Merge tag 'm68k-for-v5.10-tag1' of git://git.kernel.org/pub/scm/linux/kernel/git/geert/linux-m68k

Pull m68k updates from Geert Uytterhoeven:

  - Conversion of the Mac IDE driver to a platform driver

  - Minor cleanups and fixes

* tag 'm68k-for-v5.10-tag1' of git://git.kernel.org/pub/scm/linux/kernel/git/geert/linux-m68k:
  ide/macide: Convert Mac IDE driver to platform driver
  m68k: Replace HTTP links with HTTPS ones
  m68k: mm: Remove superfluous memblock_alloc*() casts
  m68k: mm: Use PAGE_ALIGNED() helper
  m68k: Sort selects in main Kconfig
  m68k: amiga: Clean up Amiga hardware configuration
  m68k: Revive _TIF_* masks
  m68k: Correct some typos in comments
  m68k: Use get_kernel_nofault() in show_registers()
  zorro: Fix address space collision message with RAM expansion boards
  m68k: amiga: Fix Denise detection on OCS
diff --git a/.clang-format b/.clang-format
index a0a9608..badfc1b 100644
--- a/.clang-format
+++ b/.clang-format
@@ -111,6 +111,7 @@
   - 'css_for_each_descendant_pre'
   - 'device_for_each_child_node'
   - 'dma_fence_chain_for_each'
+  - 'do_for_each_ftrace_op'
   - 'drm_atomic_crtc_for_each_plane'
   - 'drm_atomic_crtc_state_for_each_plane'
   - 'drm_atomic_crtc_state_for_each_plane_state'
@@ -136,6 +137,7 @@
   - 'for_each_active_dev_scope'
   - 'for_each_active_drhd_unit'
   - 'for_each_active_iommu'
+  - 'for_each_aggr_pgid'
   - 'for_each_available_child_of_node'
   - 'for_each_bio'
   - 'for_each_board_func_rsrc'
@@ -234,6 +236,7 @@
   - 'for_each_node_state'
   - 'for_each_node_with_cpus'
   - 'for_each_node_with_property'
+  - 'for_each_nonreserved_multicast_dest_pgid'
   - 'for_each_of_allnodes'
   - 'for_each_of_allnodes_from'
   - 'for_each_of_cpu_node'
@@ -256,6 +259,7 @@
   - 'for_each_pci_dev'
   - 'for_each_pci_msi_entry'
   - 'for_each_pcm_streams'
+  - 'for_each_physmem_range'
   - 'for_each_populated_zone'
   - 'for_each_possible_cpu'
   - 'for_each_present_cpu'
@@ -265,6 +269,8 @@
   - 'for_each_process_thread'
   - 'for_each_property_of_node'
   - 'for_each_registered_fb'
+  - 'for_each_requested_gpio'
+  - 'for_each_requested_gpio_in_range'
   - 'for_each_reserved_mem_region'
   - 'for_each_rtd_codec_dais'
   - 'for_each_rtd_codec_dais_rollback'
@@ -278,12 +284,17 @@
   - 'for_each_sg'
   - 'for_each_sg_dma_page'
   - 'for_each_sg_page'
+  - 'for_each_sgtable_dma_page'
+  - 'for_each_sgtable_dma_sg'
+  - 'for_each_sgtable_page'
+  - 'for_each_sgtable_sg'
   - 'for_each_sibling_event'
   - 'for_each_subelement'
   - 'for_each_subelement_extid'
   - 'for_each_subelement_id'
   - '__for_each_thread'
   - 'for_each_thread'
+  - 'for_each_unicast_dest_pgid'
   - 'for_each_wakeup_source'
   - 'for_each_zone'
   - 'for_each_zone_zonelist'
@@ -464,6 +475,7 @@
   - 'v4l2_m2m_for_each_src_buf'
   - 'v4l2_m2m_for_each_src_buf_safe'
   - 'virtio_device_for_each_vq'
+  - 'while_for_each_ftrace_op'
   - 'xa_for_each'
   - 'xa_for_each_marked'
   - 'xa_for_each_range'
diff --git a/.mailmap b/.mailmap
index 57fe008..0894a8b 100644
--- a/.mailmap
+++ b/.mailmap
@@ -15,32 +15,34 @@
 Aaron Durbin <adurbin@google.com>
 Adam Oldham <oldhamca@gmail.com>
 Adam Radford <aradford@gmail.com>
-Adrian Bunk <bunk@stusta.de>
 Adriana Reus <adi.reus@gmail.com> <adriana.reus@intel.com>
+Adrian Bunk <bunk@stusta.de>
 Alan Cox <alan@lxorguk.ukuu.org.uk>
 Alan Cox <root@hraefn.swansea.linux.org.uk>
-Aleksey Gorelov <aleksey_gorelov@phoenix.com>
 Aleksandar Markovic <aleksandar.markovic@mips.com> <aleksandar.markovic@imgtec.com>
-Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@intel.com>
-Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@linaro.org>
+Aleksey Gorelov <aleksey_gorelov@phoenix.com>
 Alexander Lobakin <alobakin@pm.me> <alobakin@dlink.ru>
 Alexander Lobakin <alobakin@pm.me> <alobakin@marvell.com>
 Alexander Lobakin <alobakin@pm.me> <bloodyreaper@yandex.ru>
 Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electrons.com>
-Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
 Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
 Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
+Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
+Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@intel.com>
+Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@linaro.org>
 Al Viro <viro@ftp.linux.org.uk>
 Al Viro <viro@zenIV.linux.org.uk>
+Andi Kleen <ak@linux.intel.com> <ak@suse.de>
 Andi Shyti <andi@etezian.org> <andi.shyti@samsung.com>
 Andreas Herrmann <aherrman@de.ibm.com>
-Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
 Andrew Morton <akpm@linux-foundation.org>
-Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com>
 Andrew Murray <amurray@thegoodpenguin.co.uk> <amurray@embedded-bits.co.uk>
+Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com>
 Andrew Vasquez <andrew.vasquez@qlogic.com>
+Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
 Andy Adamson <andros@citi.umich.edu>
-Antoine Tenart <antoine.tenart@free-electrons.com>
+Antoine Tenart <atenart@kernel.org> <antoine.tenart@bootlin.com>
+Antoine Tenart <atenart@kernel.org> <antoine.tenart@free-electrons.com>
 Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com>
 Archit Taneja <archit@ti.com>
 Ard Biesheuvel <ardb@kernel.org> <ard.biesheuvel@linaro.org>
@@ -48,40 +50,42 @@
 Arnd Bergmann <arnd@arndb.de>
 Axel Dyks <xl@xlsigned.net>
 Axel Lin <axel.lin@gmail.com>
-Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com>
 Bart Van Assche <bvanassche@acm.org> <bart.vanassche@sandisk.com>
+Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com>
 Ben Gardner <bgardner@wabtec.com>
 Ben M Cahill <ben.m.cahill@intel.com>
 Björn Steinbrink <B.Steinbrink@gmx.de>
-Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com>
-Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com>
 Boris Brezillon <bbrezillon@kernel.org> <b.brezillon.dev@gmail.com>
 Boris Brezillon <bbrezillon@kernel.org> <b.brezillon@overkiz.com>
+Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com>
+Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com>
 Brian Avery <b.avery@hp.com>
 Brian King <brking@us.ibm.com>
+Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
+Changbin Du <changbin.du@intel.com> <changbin.du@intel.com>
 Chao Yu <chao@kernel.org> <chao2.yu@samsung.com>
 Chao Yu <chao@kernel.org> <yuchao0@huawei.com>
-Christoph Hellwig <hch@lst.de>
 Christophe Ricard <christophe.ricard@gmail.com>
+Christoph Hellwig <hch@lst.de>
 Corey Minyard <minyard@acm.org>
 Damian Hobson-Garcia <dhobsong@igel.co.jp>
-Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
-Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
+Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com>
 Daniel Borkmann <daniel@iogearbox.net> <danborkmann@iogearbox.net>
 Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch>
-Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com>
+Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
+Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com>
 David Brownell <david-b@pacbell.net>
 David Woodhouse <dwmw2@shinybook.infradead.org>
-Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com>
-Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com>
 Dengcheng Zhu <dzhu@wavecomp.com> <dczhu@mips.com>
 Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@gmail.com>
+Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com>
+Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com>
 <dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be>
 Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
-Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
-Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
 Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com>
+Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
+Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
 Domen Puncer <domen@coderock.org>
 Douglas Gilbert <dougg@torque.net>
 Ed L. Cashin <ecashin@coraid.com>
@@ -92,20 +96,22 @@
 Felix Moeller <felix@derklecks.de>
 Filipe Lautert <filipe@icewall.org>
 Franck Bui-Huu <vagabon.xyz@gmail.com>
-Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com>
 Frank Rowand <frowand.list@gmail.com> <frank.rowand@am.sony.com>
 Frank Rowand <frowand.list@gmail.com> <frank.rowand@sonymobile.com>
+Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com>
 Frank Zago <fzago@systemfabricworks.com>
 Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com>
-Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
+Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@linux.vnet.ibm.com>
 Greg Kroah-Hartman <greg@echidna.(none)>
 Greg Kroah-Hartman <gregkh@suse.de>
 Greg Kroah-Hartman <greg@kroah.com>
 Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com>
 Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com>
+Gustavo Padovan <gustavo@las.ic.unicamp.br>
+Gustavo Padovan <padovan@profusion.mobi>
 Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org>
 Heiko Carstens <hca@linux.ibm.com> <h.carstens@de.ibm.com>
 Heiko Carstens <hca@linux.ibm.com> <heiko.carstens@de.ibm.com>
@@ -115,32 +121,33 @@
 Herbert Xu <herbert@gondor.apana.org.au>
 Jacob Shin <Jacob.Shin@amd.com>
 Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@google.com>
-Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@motorola.com>
 Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk.kim@samsung.com>
+Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@motorola.com>
 Jakub Kicinski <kuba@kernel.org> <jakub.kicinski@netronome.com>
 James Bottomley <jejb@mulgrave.(none)>
 James Bottomley <jejb@titanic.il.steeleye.com>
 James E Wilson <wilson@specifix.com>
-James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
 James Hogan <jhogan@kernel.org> <james@albanarts.com>
+James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
 James Ketrenos <jketreno@io.(none)>
 Jan Glauber <jan.glauber@gmail.com> <jang@de.ibm.com>
 Jan Glauber <jan.glauber@gmail.com> <jang@linux.vnet.ibm.com>
 Jan Glauber <jan.glauber@gmail.com> <jglauber@cavium.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com>
+Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com>
-Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 <javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
+Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com>
 Jayachandran C <c.jayachandran@gmail.com> <jchandra@broadcom.com>
 Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com>
 Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com>
-Jean Tourrilhes <jt@hpl.hp.com>
 <jean-philippe@linaro.org> <jean-philippe.brucker@arm.com>
+Jean Tourrilhes <jt@hpl.hp.com>
 Jeff Garzik <jgarzik@pretzel.yyz.us>
-Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com>
 Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net>
 Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com>
+Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com>
 Jens Axboe <axboe@suse.de>
 Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
 Jiri Slaby <jirislaby@kernel.org> <jirislaby@gmail.com>
@@ -163,31 +170,37 @@
 Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com>
 Kamil Konieczny <k.konieczny@samsung.com> <k.konieczny@partner.samsung.com>
 Kay Sievers <kay.sievers@vrfy.org>
+Kees Cook <keescook@chromium.org> <kees.cook@canonical.com>
+Kees Cook <keescook@chromium.org> <keescook@google.com>
+Kees Cook <keescook@chromium.org> <kees@outflux.net>
+Kees Cook <keescook@chromium.org> <kees@ubuntu.com>
 Kenneth W Chen <kenneth.w.chen@intel.com>
-Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
 Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru>
+Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
 Koushik <raghavendra.koushik@neterion.com>
-Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com>
 Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com>
+Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com>
 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
-Leon Romanovsky <leon@kernel.org> <leon@leon.nu>
-Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com>
 Leonardo Bras <leobras.c@gmail.com> <leonardo@linux.ibm.com>
 Leonid I Ananiev <leonid.i.ananiev@intel.com>
+Leon Romanovsky <leon@kernel.org> <leon@leon.nu>
+Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com>
+Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com>
 Linas Vepstas <linas@austin.ibm.com>
-Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
-Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
+Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
+<linux-hardening@vger.kernel.org> <kernel-hardening@lists.openwall.com>
 Li Yang <leoyang.li@nxp.com> <leoli@freescale.com>
+Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
 Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com>
 Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
-Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com>
 Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com>
+Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com>
 Mark Brown <broonie@sirena.org.uk>
 Mark Yao <markyao0591@gmail.com> <mark.yao@rock-chips.com>
-Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com>
 Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com>
 Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm>
+Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com>
 Mathieu Othacehe <m.othacehe@gmail.com>
 Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com>
 Matthew Wilcox <willy@infradead.org> <matthew@wil.cx>
@@ -197,17 +210,17 @@
 Matthew Wilcox <willy@infradead.org> <willy@linux.intel.com>
 Matthew Wilcox <willy@infradead.org> <willy@parisc-linux.org>
 Matthieu CASTET <castet.matthieu@free.fr>
-Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br>
-Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com>
-Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@infradead.org>
-Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@redhat.com>
-Mauro Carvalho Chehab <mchehab@kernel.org> <m.chehab@samsung.com>
-Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@osg.samsung.com>
-Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@s-opensource.com>
+Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting>
 Matt Ranostay <mranostay@gmail.com> Matthew Ranostay <mranostay@embeddedalley.com>
 Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com>
-Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting>
 Matt Redfearn <matt.redfearn@mips.com> <matt.redfearn@imgtec.com>
+Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com>
+Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br>
+Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@infradead.org>
+Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@osg.samsung.com>
+Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@redhat.com>
+Mauro Carvalho Chehab <mchehab@kernel.org> <m.chehab@samsung.com>
+Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@s-opensource.com>
 Maxime Ripard <mripard@kernel.org> <maxime.ripard@bootlin.com>
 Maxime Ripard <mripard@kernel.org> <maxime.ripard@free-electrons.com>
 Mayuresh Janorkar <mayur@ti.com>
@@ -239,13 +252,13 @@
 Patrick Mochel <mochel@digitalimplant.org>
 Paul Burton <paulburton@kernel.org> <paul.burton@imgtec.com>
 Paul Burton <paulburton@kernel.org> <paul.burton@mips.com>
+Paul E. McKenney <paulmck@kernel.org> <paul.mckenney@linaro.org>
 Paul E. McKenney <paulmck@kernel.org> <paulmck@linux.ibm.com>
 Paul E. McKenney <paulmck@kernel.org> <paulmck@linux.vnet.ibm.com>
-Paul E. McKenney <paulmck@kernel.org> <paul.mckenney@linaro.org>
 Paul E. McKenney <paulmck@kernel.org> <paulmck@us.ibm.com>
 Peter A Jonsson <pj@ludd.ltu.se>
-Peter Oruba <peter@oruba.de>
 Peter Oruba <peter.oruba@amd.com>
+Peter Oruba <peter@oruba.de>
 Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com>
 Praveen BP <praveenbp@ti.com>
 Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com>
@@ -258,23 +271,23 @@
 Ralf Wildenhues <Ralf.Wildenhues@gmx.de>
 Randy Dunlap <rdunlap@infradead.org> <rdunlap@xenotime.net>
 Rémi Denis-Courmont <rdenis@simphalempin.com>
-Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com>
 Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com>
 Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org>
+Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com>
 Ross Zwisler <zwisler@kernel.org> <ross.zwisler@linux.intel.com>
 Rudolf Marek <R.Marek@sh.cvut.cz>
 Rui Saraiva <rmps@joel.ist.utl.pt>
 Sachin P Sant <ssant@in.ibm.com>
-Sarangdhar Joshi <spjoshi@codeaurora.org>
+Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi>
 Sam Ravnborg <sam@mars.ravnborg.org>
-Santosh Shilimkar <ssantosh@kernel.org>
 Santosh Shilimkar <santosh.shilimkar@oracle.org>
+Santosh Shilimkar <ssantosh@kernel.org>
+Sarangdhar Joshi <spjoshi@codeaurora.org>
 Sascha Hauer <s.hauer@pengutronix.de>
 S.Ça─člar Onur <caglar@pardus.org.tr>
-Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi>
 Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk>
-Sebastian Reichel <sre@kernel.org> <sre@debian.org>
 Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk>
+Sebastian Reichel <sre@kernel.org> <sre@debian.org>
 Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de>
 Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com>
 Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com>
@@ -285,19 +298,23 @@
 Simon Kelley <simon@thekelleys.org.uk>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
 Stephen Hemminger <shemminger@osdl.org>
+Steve Wise <larrystevenwise@gmail.com> <swise@chelsio.com>
+Steve Wise <larrystevenwise@gmail.com> <swise@opengridcomputing.com>
 Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
 Subhash Jadavani <subhashj@codeaurora.org>
 Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
 Sumit Semwal <sumit.semwal@ti.com>
+Takashi YOSHII <takashi.yoshii.zj@renesas.com>
 Tejun Heo <htejun@gmail.com>
 Thomas Graf <tgraf@suug.ch>
 Thomas Pedersen <twp@codeaurora.org>
 Tiezhu Yang <yangtiezhu@loongson.cn> <kernelpatch@126.com>
 Todor Tomov <todor.too@gmail.com> <todor.tomov@linaro.org>
 Tony Luck <tony.luck@intel.com>
-TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
 TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org>
+TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
 Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
+Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
 Uwe Kleine-König <ukl@pengutronix.de>
 Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com>
@@ -305,22 +322,16 @@
 Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com>
 Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com>
 Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org>
+Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com>
 Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com>
 Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com>
-Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com>
 Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com>
 Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com>
-Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
 Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
-Takashi YOSHII <takashi.yoshii.zj@renesas.com>
+Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
+WeiXiong Liao <gmpy.liaowx@gmail.com> <liaoweixiong@allwinnertech.com>
 Will Deacon <will@kernel.org> <will.deacon@arm.com>
-Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de>
 Wolfram Sang <wsa@kernel.org> <w.sang@pengutronix.de>
+Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de>
 Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com>
 Yusuke Goda <goda.yusuke@renesas.com>
-Gustavo Padovan <gustavo@las.ic.unicamp.br>
-Gustavo Padovan <padovan@profusion.mobi>
-Changbin Du <changbin.du@intel.com> <changbin.du@intel.com>
-Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
-Steve Wise <larrystevenwise@gmail.com> <swise@chelsio.com>
-Steve Wise <larrystevenwise@gmail.com> <swise@opengridcomputing.com>
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
index f7e32f2..e82fc37 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
@@ -43,7 +43,7 @@
 		This sysfs interface exposes the number of cores per chip
 		present in the system.
 
-What:		/sys/devices/hv_24x7/interface/cpumask
+What:		/sys/devices/hv_24x7/cpumask
 Date:		July 2020
 Contact:	Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
 Description:	read only
diff --git a/Documentation/RCU/lockdep.rst b/Documentation/RCU/lockdep.rst
index f1fc8ae..cc860a0 100644
--- a/Documentation/RCU/lockdep.rst
+++ b/Documentation/RCU/lockdep.rst
@@ -49,7 +49,7 @@
 		is invoked by both RCU-sched readers and updaters.
 	srcu_dereference_check(p, c):
 		Use explicit check expression "c" along with
-		srcu_read_lock_held()().  This is useful in code that
+		srcu_read_lock_held().  This is useful in code that
 		is invoked by both SRCU readers and updaters.
 	rcu_dereference_raw(p):
 		Don't check.  (Use sparingly, if at all.)
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 6be4378..baa07b3 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1324,15 +1324,26 @@
 	  pgmajfault
 		Number of major page faults incurred
 
-	  workingset_refault
-		Number of refaults of previously evicted pages
+	  workingset_refault_anon
+		Number of refaults of previously evicted anonymous pages.
 
-	  workingset_activate
-		Number of refaulted pages that were immediately activated
+	  workingset_refault_file
+		Number of refaults of previously evicted file pages.
 
-	  workingset_restore
-		Number of restored pages which have been detected as an active
-		workingset before they got reclaimed.
+	  workingset_activate_anon
+		Number of refaulted anonymous pages that were immediately
+		activated.
+
+	  workingset_activate_file
+		Number of refaulted file pages that were immediately activated.
+
+	  workingset_restore_anon
+		Number of restored anonymous pages which have been detected as
+		an active workingset before they got reclaimed.
+
+	  workingset_restore_file
+		Number of restored file pages which have been detected as an
+		active workingset before they got reclaimed.
 
 	  workingset_nodereclaim
 		Number of times a shadow node has been reclaimed
diff --git a/Documentation/admin-guide/device-mapper/dm-crypt.rst b/Documentation/admin-guide/device-mapper/dm-crypt.rst
index 8f4a3f8..bc28a95 100644
--- a/Documentation/admin-guide/device-mapper/dm-crypt.rst
+++ b/Documentation/admin-guide/device-mapper/dm-crypt.rst
@@ -67,7 +67,7 @@
     the value passed in <key_size>.
 
 <key_type>
-    Either 'logon' or 'user' kernel key type.
+    Either 'logon', 'user' or 'encrypted' kernel key type.
 
 <key_description>
     The kernel keyring key description crypt target should look for
@@ -121,6 +121,14 @@
     thread because it benefits CFQ to have writes submitted using the
     same context.
 
+no_read_workqueue
+    Bypass dm-crypt internal workqueue and process read requests synchronously.
+
+no_write_workqueue
+    Bypass dm-crypt internal workqueue and process write requests synchronously.
+    This option is automatically enabled for host-managed zoned block devices
+    (e.g. host-managed SMR hard-disks).
+
 integrity:<bytes>:<type>
     The device requires additional <bytes> metadata per-sector stored
     in per-bio integrity structure. This metadata must by provided
diff --git a/Documentation/admin-guide/devices.txt b/Documentation/admin-guide/devices.txt
index d336f3f..63fd4e6 100644
--- a/Documentation/admin-guide/devices.txt
+++ b/Documentation/admin-guide/devices.txt
@@ -1662,7 +1662,7 @@
 
   98 block	User-mode virtual block device
 		  0 = /dev/ubda		First user-mode block device
-		 16 = /dev/udbb		Second user-mode block device
+		 16 = /dev/ubdb		Second user-mode block device
 		    ...
 
 		Partitions are handled in the same way as for IDE
diff --git a/Documentation/admin-guide/dynamic-debug-howto.rst b/Documentation/admin-guide/dynamic-debug-howto.rst
index e5a8def..6c04aea 100644
--- a/Documentation/admin-guide/dynamic-debug-howto.rst
+++ b/Documentation/admin-guide/dynamic-debug-howto.rst
@@ -156,7 +156,6 @@
   ``line-range`` cannot contain space, e.g.
   "1-30" is valid range but "1 - 30" is not.
 
-  ``module=foo`` combined keyword=value form is interchangably accepted
 
 The meanings of each keyword are:
 
diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst
index a683976..d2795ca 100644
--- a/Documentation/admin-guide/ext4.rst
+++ b/Documentation/admin-guide/ext4.rst
@@ -489,6 +489,9 @@
         multiple of this tuning parameter if the stripe size is not set in the
         ext4 superblock
 
+  mb_max_inode_prealloc
+        The maximum length of per-inode ext4_prealloc_space list.
+
   mb_max_to_scan
         The maximum number of extents the multiblock allocator will search to
         find the best extent.
@@ -529,21 +532,21 @@
 Ioctls
 ======
 
-There is some Ext4 specific functionality which can be accessed by applications
-through the system call interfaces. The list of all Ext4 specific ioctls are
-shown in the table below.
+Ext4 implements various ioctls which can be used by applications to access
+ext4-specific functionality. An incomplete list of these ioctls is shown in the
+table below. This list includes truly ext4-specific ioctls (``EXT4_IOC_*``) as
+well as ioctls that may have been ext4-specific originally but are now supported
+by some other filesystem(s) too (``FS_IOC_*``).
 
-Table of Ext4 specific ioctls
+Table of Ext4 ioctls
 
-  EXT4_IOC_GETFLAGS
+  FS_IOC_GETFLAGS
         Get additional attributes associated with inode.  The ioctl argument is
-        an integer bitfield, with bit values described in ext4.h. This ioctl is
-        an alias for FS_IOC_GETFLAGS.
+        an integer bitfield, with bit values described in ext4.h.
 
-  EXT4_IOC_SETFLAGS
+  FS_IOC_SETFLAGS
         Set additional attributes associated with inode.  The ioctl argument is
-        an integer bitfield, with bit values described in ext4.h. This ioctl is
-        an alias for FS_IOC_SETFLAGS.
+        an integer bitfield, with bit values described in ext4.h.
 
   EXT4_IOC_GETVERSION, EXT4_IOC_GETVERSION_OLD
         Get the inode i_generation number stored for each inode. The
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index bdc1f33..a106874 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1233,8 +1233,7 @@
 	efi=		[EFI]
 			Format: { "debug", "disable_early_pci_dma",
 				  "nochunk", "noruntime", "nosoftreserve",
-				  "novamap", "no_disable_early_pci_dma",
-				  "old_map" }
+				  "novamap", "no_disable_early_pci_dma" }
 			debug: enable misc debug output.
 			disable_early_pci_dma: disable the busmaster bit on all
 			PCI bridges while in the EFI boot stub.
@@ -1251,8 +1250,6 @@
 			novamap: do not call SetVirtualAddressMap().
 			no_disable_early_pci_dma: Leave the busmaster bit set
 			on all PCI bridges while in the EFI boot stub
-			old_map [X86-64]: switch to the old ioremap-based EFI
-			runtime services mapping. [Needs CONFIG_X86_UV=y]
 
 	efi_no_storage_paranoia [EFI; X86]
 			Using this parameter you can use more than 50% of
diff --git a/Documentation/admin-guide/laptops/thinkpad-acpi.rst b/Documentation/admin-guide/laptops/thinkpad-acpi.rst
index 5e477869..5fe1ade 100644
--- a/Documentation/admin-guide/laptops/thinkpad-acpi.rst
+++ b/Documentation/admin-guide/laptops/thinkpad-acpi.rst
@@ -1434,7 +1434,7 @@
 
 
 DYTC Lapmode sensor
-------------------
+-------------------
 
 sysfs: dytc_lapmode
 
diff --git a/Documentation/admin-guide/perf/arm-cmn.rst b/Documentation/admin-guide/perf/arm-cmn.rst
new file mode 100644
index 0000000..0e48093
--- /dev/null
+++ b/Documentation/admin-guide/perf/arm-cmn.rst
@@ -0,0 +1,65 @@
+=============================
+Arm Coherent Mesh Network PMU
+=============================
+
+CMN-600 is a configurable mesh interconnect consisting of a rectangular
+grid of crosspoints (XPs), with each crosspoint supporting up to two
+device ports to which various AMBA CHI agents are attached.
+
+CMN implements a distributed PMU design as part of its debug and trace
+functionality. This consists of a local monitor (DTM) at every XP, which
+counts up to 4 event signals from the connected device nodes and/or the
+XP itself. Overflow from these local counters is accumulated in up to 8
+global counters implemented by the main controller (DTC), which provides
+overall PMU control and interrupts for global counter overflow.
+
+PMU events
+----------
+
+The PMU driver registers a single PMU device for the whole interconnect,
+see /sys/bus/event_source/devices/arm_cmn. Multi-chip systems may link
+more than one CMN together via external CCIX links - in this situation,
+each mesh counts its own events entirely independently, and additional
+PMU devices will be named arm_cmn_{1..n}.
+
+Most events are specified in a format based directly on the TRM
+definitions - "type" selects the respective node type, and "eventid" the
+event number. Some events require an additional occupancy ID, which is
+specified by "occupid".
+
+* Since RN-D nodes do not have any distinct events from RN-I nodes, they
+  are treated as the same type (0xa), and the common event templates are
+  named "rnid_*".
+
+* The cycle counter is treated as a synthetic event belonging to the DTC
+  node ("type" == 0x3, "eventid" is ignored).
+
+* XP events also encode the port and channel in the "eventid" field, to
+  match the underlying pmu_event0_id encoding for the pmu_event_sel
+  register. The event templates are named with prefixes to cover all
+  permutations.
+
+By default each event provides an aggregate count over all nodes of the
+given type. To target a specific node, "bynodeid" must be set to 1 and
+"nodeid" to the appropriate value derived from the CMN configuration
+(as defined in the "Node ID Mapping" section of the TRM).
+
+Watchpoints
+-----------
+
+The PMU can also count watchpoint events to monitor specific flit
+traffic. Watchpoints are treated as a synthetic event type, and like PMU
+events can be global or targeted with a particular XP's "nodeid" value.
+Since the watchpoint direction is otherwise implicit in the underlying
+register selection, separate events are provided for flit uploads and
+downloads.
+
+The flit match value and mask are passed in config1 and config2 ("val"
+and "mask" respectively). "wp_dev_sel", "wp_chn_sel", "wp_grp" and
+"wp_exclusive" are specified per the TRM definitions for dtm_wp_config0.
+Where a watchpoint needs to match fields from both match groups on the
+REQ or SNP channel, it can be specified as two events - one for each
+group - with the same nonzero "combine" value. The count for such a
+pair of combined events will be attributed to the primary match.
+Watchpoint events with a "combine" value of 0 are considered independent
+and will count individually.
diff --git a/Documentation/admin-guide/perf/index.rst b/Documentation/admin-guide/perf/index.rst
index 47c99f4..5a8f252 100644
--- a/Documentation/admin-guide/perf/index.rst
+++ b/Documentation/admin-guide/perf/index.rst
@@ -12,6 +12,7 @@
    qcom_l2_pmu
    qcom_l3_pmu
    arm-ccn
+   arm-cmn
    xgene-pmu
    arm_dsu_pmu
    thunderx2-pmu
diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst
index a96a423..6ebe163 100644
--- a/Documentation/admin-guide/pm/cpuidle.rst
+++ b/Documentation/admin-guide/pm/cpuidle.rst
@@ -690,7 +690,7 @@
 instruction of the CPUs (which, as a rule, suspends the execution of the program
 and causes the hardware to attempt to enter the shallowest available idle state)
 for this purpose, and if ``idle=poll`` is used, idle CPUs will execute a
-more or less ``lightweight'' sequence of instructions in a tight loop.  [Note
+more or less "lightweight" sequence of instructions in a tight loop.  [Note
 that using ``idle=poll`` is somewhat drastic in many cases, as preventing idle
 CPUs from saving almost any energy at all may not be the only effect of it.
 For example, on Intel hardware it effectively prevents CPUs from using
diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst
index 7adef96..5072e70 100644
--- a/Documentation/admin-guide/pm/intel_pstate.rst
+++ b/Documentation/admin-guide/pm/intel_pstate.rst
@@ -123,7 +123,9 @@
 internal P-state selection logic is expected to focus entirely on performance.
 
 This will override the EPP/EPB setting coming from the ``sysfs`` interface
-(see `Energy vs Performance Hints`_ below).
+(see `Energy vs Performance Hints`_ below).  Moreover, any attempts to change
+the EPP/EPB to a value different from 0 ("performance") via ``sysfs`` in this
+configuration will be rejected.
 
 Also, in this configuration the range of P-states available to the processor's
 internal P-state selection logic is always restricted to the upper boundary
@@ -564,8 +566,8 @@
 Energy-Performance Bias (EPB) knob. It is also possible to write a positive
 integer value between 0 to 255, if the EPP feature is present. If the EPP
 feature is not present, writing integer value to this attribute is not
-supported. In this case, user can use
- "/sys/devices/system/cpu/cpu*/power/energy_perf_bias" interface.
+supported. In this case, user can use the
+"/sys/devices/system/cpu/cpu*/power/energy_perf_bias" interface.
 
 [Note that tasks may by migrated from one CPU to another by the scheduler's
 load-balancing algorithm and if different energy vs performance hints are
diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst
index f28853f..328e0c4 100644
--- a/Documentation/arm64/cpu-feature-registers.rst
+++ b/Documentation/arm64/cpu-feature-registers.rst
@@ -175,6 +175,8 @@
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
+     | MTE                          | [11-8]  |    y    |
+     +------------------------------+---------+---------+
      | SSBS                         | [7-4]   |    y    |
      +------------------------------+---------+---------+
      | BT                           | [3-0]   |    y    |
diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst
index 84a9fd2..bbd9cf5 100644
--- a/Documentation/arm64/elf_hwcaps.rst
+++ b/Documentation/arm64/elf_hwcaps.rst
@@ -240,6 +240,10 @@
 
     Functionality implied by ID_AA64PFR0_EL1.BT == 0b0001.
 
+HWCAP2_MTE
+
+    Functionality implied by ID_AA64PFR1_EL1.MTE == 0b0010, as described
+    by Documentation/arm64/memory-tagging-extension.rst.
 
 4. Unused AT_HWCAP bits
 -----------------------
diff --git a/Documentation/arm64/index.rst b/Documentation/arm64/index.rst
index d9665d8..43b0939 100644
--- a/Documentation/arm64/index.rst
+++ b/Documentation/arm64/index.rst
@@ -14,6 +14,7 @@
     hugetlbpage
     legacy_instructions
     memory
+    memory-tagging-extension
     perf
     pointer-authentication
     silicon-errata
diff --git a/Documentation/arm64/memory-tagging-extension.rst b/Documentation/arm64/memory-tagging-extension.rst
new file mode 100644
index 0000000..034d37c
--- /dev/null
+++ b/Documentation/arm64/memory-tagging-extension.rst
@@ -0,0 +1,305 @@
+===============================================
+Memory Tagging Extension (MTE) in AArch64 Linux
+===============================================
+
+Authors: Vincenzo Frascino <vincenzo.frascino@arm.com>
+         Catalin Marinas <catalin.marinas@arm.com>
+
+Date: 2020-02-25
+
+This document describes the provision of the Memory Tagging Extension
+functionality in AArch64 Linux.
+
+Introduction
+============
+
+ARMv8.5 based processors introduce the Memory Tagging Extension (MTE)
+feature. MTE is built on top of the ARMv8.0 virtual address tagging TBI
+(Top Byte Ignore) feature and allows software to access a 4-bit
+allocation tag for each 16-byte granule in the physical address space.
+Such memory range must be mapped with the Normal-Tagged memory
+attribute. A logical tag is derived from bits 59-56 of the virtual
+address used for the memory access. A CPU with MTE enabled will compare
+the logical tag against the allocation tag and potentially raise an
+exception on mismatch, subject to system registers configuration.
+
+Userspace Support
+=================
+
+When ``CONFIG_ARM64_MTE`` is selected and Memory Tagging Extension is
+supported by the hardware, the kernel advertises the feature to
+userspace via ``HWCAP2_MTE``.
+
+PROT_MTE
+--------
+
+To access the allocation tags, a user process must enable the Tagged
+memory attribute on an address range using a new ``prot`` flag for
+``mmap()`` and ``mprotect()``:
+
+``PROT_MTE`` - Pages allow access to the MTE allocation tags.
+
+The allocation tag is set to 0 when such pages are first mapped in the
+user address space and preserved on copy-on-write. ``MAP_SHARED`` is
+supported and the allocation tags can be shared between processes.
+
+**Note**: ``PROT_MTE`` is only supported on ``MAP_ANONYMOUS`` and
+RAM-based file mappings (``tmpfs``, ``memfd``). Passing it to other
+types of mapping will result in ``-EINVAL`` returned by these system
+calls.
+
+**Note**: The ``PROT_MTE`` flag (and corresponding memory type) cannot
+be cleared by ``mprotect()``.
+
+**Note**: ``madvise()`` memory ranges with ``MADV_DONTNEED`` and
+``MADV_FREE`` may have the allocation tags cleared (set to 0) at any
+point after the system call.
+
+Tag Check Faults
+----------------
+
+When ``PROT_MTE`` is enabled on an address range and a mismatch between
+the logical and allocation tags occurs on access, there are three
+configurable behaviours:
+
+- *Ignore* - This is the default mode. The CPU (and kernel) ignores the
+  tag check fault.
+
+- *Synchronous* - The kernel raises a ``SIGSEGV`` synchronously, with
+  ``.si_code = SEGV_MTESERR`` and ``.si_addr = <fault-address>``. The
+  memory access is not performed. If ``SIGSEGV`` is ignored or blocked
+  by the offending thread, the containing process is terminated with a
+  ``coredump``.
+
+- *Asynchronous* - The kernel raises a ``SIGSEGV``, in the offending
+  thread, asynchronously following one or multiple tag check faults,
+  with ``.si_code = SEGV_MTEAERR`` and ``.si_addr = 0`` (the faulting
+  address is unknown).
+
+The user can select the above modes, per thread, using the
+``prctl(PR_SET_TAGGED_ADDR_CTRL, flags, 0, 0, 0)`` system call where
+``flags`` contain one of the following values in the ``PR_MTE_TCF_MASK``
+bit-field:
+
+- ``PR_MTE_TCF_NONE``  - *Ignore* tag check faults
+- ``PR_MTE_TCF_SYNC``  - *Synchronous* tag check fault mode
+- ``PR_MTE_TCF_ASYNC`` - *Asynchronous* tag check fault mode
+
+The current tag check fault mode can be read using the
+``prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0)`` system call.
+
+Tag checking can also be disabled for a user thread by setting the
+``PSTATE.TCO`` bit with ``MSR TCO, #1``.
+
+**Note**: Signal handlers are always invoked with ``PSTATE.TCO = 0``,
+irrespective of the interrupted context. ``PSTATE.TCO`` is restored on
+``sigreturn()``.
+
+**Note**: There are no *match-all* logical tags available for user
+applications.
+
+**Note**: Kernel accesses to the user address space (e.g. ``read()``
+system call) are not checked if the user thread tag checking mode is
+``PR_MTE_TCF_NONE`` or ``PR_MTE_TCF_ASYNC``. If the tag checking mode is
+``PR_MTE_TCF_SYNC``, the kernel makes a best effort to check its user
+address accesses, however it cannot always guarantee it.
+
+Excluding Tags in the ``IRG``, ``ADDG`` and ``SUBG`` instructions
+-----------------------------------------------------------------
+
+The architecture allows excluding certain tags to be randomly generated
+via the ``GCR_EL1.Exclude`` register bit-field. By default, Linux
+excludes all tags other than 0. A user thread can enable specific tags
+in the randomly generated set using the ``prctl(PR_SET_TAGGED_ADDR_CTRL,
+flags, 0, 0, 0)`` system call where ``flags`` contains the tags bitmap
+in the ``PR_MTE_TAG_MASK`` bit-field.
+
+**Note**: The hardware uses an exclude mask but the ``prctl()``
+interface provides an include mask. An include mask of ``0`` (exclusion
+mask ``0xffff``) results in the CPU always generating tag ``0``.
+
+Initial process state
+---------------------
+
+On ``execve()``, the new process has the following configuration:
+
+- ``PR_TAGGED_ADDR_ENABLE`` set to 0 (disabled)
+- Tag checking mode set to ``PR_MTE_TCF_NONE``
+- ``PR_MTE_TAG_MASK`` set to 0 (all tags excluded)
+- ``PSTATE.TCO`` set to 0
+- ``PROT_MTE`` not set on any of the initial memory maps
+
+On ``fork()``, the new process inherits the parent's configuration and
+memory map attributes with the exception of the ``madvise()`` ranges
+with ``MADV_WIPEONFORK`` which will have the data and tags cleared (set
+to 0).
+
+The ``ptrace()`` interface
+--------------------------
+
+``PTRACE_PEEKMTETAGS`` and ``PTRACE_POKEMTETAGS`` allow a tracer to read
+the tags from or set the tags to a tracee's address space. The
+``ptrace()`` system call is invoked as ``ptrace(request, pid, addr,
+data)`` where:
+
+- ``request`` - one of ``PTRACE_PEEKMTETAGS`` or ``PTRACE_POKEMTETAGS``.
+- ``pid`` - the tracee's PID.
+- ``addr`` - address in the tracee's address space.
+- ``data`` - pointer to a ``struct iovec`` where ``iov_base`` points to
+  a buffer of ``iov_len`` length in the tracer's address space.
+
+The tags in the tracer's ``iov_base`` buffer are represented as one
+4-bit tag per byte and correspond to a 16-byte MTE tag granule in the
+tracee's address space.
+
+**Note**: If ``addr`` is not aligned to a 16-byte granule, the kernel
+will use the corresponding aligned address.
+
+``ptrace()`` return value:
+
+- 0 - tags were copied, the tracer's ``iov_len`` was updated to the
+  number of tags transferred. This may be smaller than the requested
+  ``iov_len`` if the requested address range in the tracee's or the
+  tracer's space cannot be accessed or does not have valid tags.
+- ``-EPERM`` - the specified process cannot be traced.
+- ``-EIO`` - the tracee's address range cannot be accessed (e.g. invalid
+  address) and no tags copied. ``iov_len`` not updated.
+- ``-EFAULT`` - fault on accessing the tracer's memory (``struct iovec``
+  or ``iov_base`` buffer) and no tags copied. ``iov_len`` not updated.
+- ``-EOPNOTSUPP`` - the tracee's address does not have valid tags (never
+  mapped with the ``PROT_MTE`` flag). ``iov_len`` not updated.
+
+**Note**: There are no transient errors for the requests above, so user
+programs should not retry in case of a non-zero system call return.
+
+``PTRACE_GETREGSET`` and ``PTRACE_SETREGSET`` with ``addr ==
+``NT_ARM_TAGGED_ADDR_CTRL`` allow ``ptrace()`` access to the tagged
+address ABI control and MTE configuration of a process as per the
+``prctl()`` options described in
+Documentation/arm64/tagged-address-abi.rst and above. The corresponding
+``regset`` is 1 element of 8 bytes (``sizeof(long))``).
+
+Example of correct usage
+========================
+
+*MTE Example code*
+
+.. code-block:: c
+
+    /*
+     * To be compiled with -march=armv8.5-a+memtag
+     */
+    #include <errno.h>
+    #include <stdint.h>
+    #include <stdio.h>
+    #include <stdlib.h>
+    #include <unistd.h>
+    #include <sys/auxv.h>
+    #include <sys/mman.h>
+    #include <sys/prctl.h>
+
+    /*
+     * From arch/arm64/include/uapi/asm/hwcap.h
+     */
+    #define HWCAP2_MTE              (1 << 18)
+
+    /*
+     * From arch/arm64/include/uapi/asm/mman.h
+     */
+    #define PROT_MTE                 0x20
+
+    /*
+     * From include/uapi/linux/prctl.h
+     */
+    #define PR_SET_TAGGED_ADDR_CTRL 55
+    #define PR_GET_TAGGED_ADDR_CTRL 56
+    # define PR_TAGGED_ADDR_ENABLE  (1UL << 0)
+    # define PR_MTE_TCF_SHIFT       1
+    # define PR_MTE_TCF_NONE        (0UL << PR_MTE_TCF_SHIFT)
+    # define PR_MTE_TCF_SYNC        (1UL << PR_MTE_TCF_SHIFT)
+    # define PR_MTE_TCF_ASYNC       (2UL << PR_MTE_TCF_SHIFT)
+    # define PR_MTE_TCF_MASK        (3UL << PR_MTE_TCF_SHIFT)
+    # define PR_MTE_TAG_SHIFT       3
+    # define PR_MTE_TAG_MASK        (0xffffUL << PR_MTE_TAG_SHIFT)
+
+    /*
+     * Insert a random logical tag into the given pointer.
+     */
+    #define insert_random_tag(ptr) ({                       \
+            uint64_t __val;                                 \
+            asm("irg %0, %1" : "=r" (__val) : "r" (ptr));   \
+            __val;                                          \
+    })
+
+    /*
+     * Set the allocation tag on the destination address.
+     */
+    #define set_tag(tagged_addr) do {                                      \
+            asm volatile("stg %0, [%0]" : : "r" (tagged_addr) : "memory"); \
+    } while (0)
+
+    int main()
+    {
+            unsigned char *a;
+            unsigned long page_sz = sysconf(_SC_PAGESIZE);
+            unsigned long hwcap2 = getauxval(AT_HWCAP2);
+
+            /* check if MTE is present */
+            if (!(hwcap2 & HWCAP2_MTE))
+                    return EXIT_FAILURE;
+
+            /*
+             * Enable the tagged address ABI, synchronous MTE tag check faults and
+             * allow all non-zero tags in the randomly generated set.
+             */
+            if (prctl(PR_SET_TAGGED_ADDR_CTRL,
+                      PR_TAGGED_ADDR_ENABLE | PR_MTE_TCF_SYNC | (0xfffe << PR_MTE_TAG_SHIFT),
+                      0, 0, 0)) {
+                    perror("prctl() failed");
+                    return EXIT_FAILURE;
+            }
+
+            a = mmap(0, page_sz, PROT_READ | PROT_WRITE,
+                     MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+            if (a == MAP_FAILED) {
+                    perror("mmap() failed");
+                    return EXIT_FAILURE;
+            }
+
+            /*
+             * Enable MTE on the above anonymous mmap. The flag could be passed
+             * directly to mmap() and skip this step.
+             */
+            if (mprotect(a, page_sz, PROT_READ | PROT_WRITE | PROT_MTE)) {
+                    perror("mprotect() failed");
+                    return EXIT_FAILURE;
+            }
+
+            /* access with the default tag (0) */
+            a[0] = 1;
+            a[1] = 2;
+
+            printf("a[0] = %hhu a[1] = %hhu\n", a[0], a[1]);
+
+            /* set the logical and allocation tags */
+            a = (unsigned char *)insert_random_tag(a);
+            set_tag(a);
+
+            printf("%p\n", a);
+
+            /* non-zero tag access */
+            a[0] = 3;
+            printf("a[0] = %hhu a[1] = %hhu\n", a[0], a[1]);
+
+            /*
+             * If MTE is enabled correctly the next instruction will generate an
+             * exception.
+             */
+            printf("Expecting SIGSEGV...\n");
+            a[16] = 0xdd;
+
+            /* this should not be printed in the PR_MTE_TCF_SYNC mode */
+            printf("...haven't got one\n");
+
+            return EXIT_FAILURE;
+    }
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index d46429b..7df2465 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -36,6 +36,12 @@
    bpf_devel_QA
 
 
+Helper functions
+================
+
+* `bpf-helpers(7)`_ maintains a list of helpers available to eBPF programs.
+
+
 Program types
 =============
 
@@ -79,4 +85,5 @@
 .. _networking-filter: ../networking/filter.rst
 .. _man-pages: https://www.kernel.org/doc/man-pages/
 .. _bpf(2): https://man7.org/linux/man-pages/man2/bpf.2.html
+.. _bpf-helpers(7): https://man7.org/linux/man-pages/man7/bpf-helpers.7.html
 .. _BPF and XDP Reference Guide: https://docs.cilium.io/en/latest/bpf/
diff --git a/Documentation/bpf/ringbuf.rst b/Documentation/bpf/ringbuf.rst
index 75f943f..6a615cd 100644
--- a/Documentation/bpf/ringbuf.rst
+++ b/Documentation/bpf/ringbuf.rst
@@ -182,9 +182,6 @@
 already committed. It is thus possible for slow producers to temporarily hold
 off submitted records, that were reserved later.
 
-Reservation/commit/consumer protocol is verified by litmus tests in
-Documentation/litmus_tests/bpf-rb/_.
-
 One interesting implementation bit, that significantly simplifies (and thus
 speeds up as well) implementation of both producers and consumers is how data
 area is mapped twice contiguously back-to-back in the virtual memory. This
@@ -200,7 +197,7 @@
 being available after commit only if consumer has already caught up right up to
 the record being committed. If not, consumer still has to catch up and thus
 will see new data anyways without needing an extra poll notification.
-Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c_) show that
+Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbufs.c) show that
 this allows to achieve a very high throughput without having to resort to
 tricks like "notify only every Nth sample", which are necessary with perf
 buffer. For extreme cases, when BPF program wants more manual control of
diff --git a/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
index 17e4f20..6834f5e 100644
--- a/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
@@ -23,7 +23,7 @@
   compatible:
     items:
       - const: raspberrypi,bcm2835-firmware
-      - const: simple-bus
+      - const: simple-mfd
 
   mboxes:
     $ref: '/schemas/types.yaml#/definitions/phandle'
@@ -57,7 +57,7 @@
 examples:
   - |
     firmware {
-        compatible = "raspberrypi,bcm2835-firmware", "simple-bus";
+        compatible = "raspberrypi,bcm2835-firmware", "simple-mfd";
         mboxes = <&mailbox>;
 
         firmware_clocks: clocks {
diff --git a/Documentation/devicetree/bindings/clock/imx23-clock.yaml b/Documentation/devicetree/bindings/clock/imx23-clock.yaml
index 66cb238..ad21899 100644
--- a/Documentation/devicetree/bindings/clock/imx23-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/imx23-clock.yaml
@@ -7,7 +7,7 @@
 title: Clock bindings for Freescale i.MX23
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 description: |
   The clock consumer should specify the desired clock by having the clock
diff --git a/Documentation/devicetree/bindings/clock/imx28-clock.yaml b/Documentation/devicetree/bindings/clock/imx28-clock.yaml
index 72328d5..f1af110 100644
--- a/Documentation/devicetree/bindings/clock/imx28-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/imx28-clock.yaml
@@ -7,7 +7,7 @@
 title: Clock bindings for Freescale i.MX28
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 description: |
   The clock consumer should specify the desired clock by having the clock
diff --git a/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml b/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml
index 85ef69f..1465c9e 100644
--- a/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml
+++ b/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml
@@ -67,7 +67,7 @@
 
     main_crypto: crypto@4e00000 {
         compatible = "ti,j721-sa2ul";
-        reg = <0x0 0x4e00000 0x0 0x1200>;
+        reg = <0x4e00000 0x1200>;
         power-domains = <&k3_pds 264 TI_SCI_PD_EXCLUSIVE>;
         dmas = <&main_udmap 0xc000>, <&main_udmap 0x4000>,
                <&main_udmap 0x4001>;
diff --git a/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml b/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml
index 52a939c..7b9d468 100644
--- a/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml
+++ b/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml
@@ -145,10 +145,10 @@
 
     display@fd4a0000 {
         compatible = "xlnx,zynqmp-dpsub-1.7";
-        reg = <0x0 0xfd4a0000 0x0 0x1000>,
-              <0x0 0xfd4aa000 0x0 0x1000>,
-              <0x0 0xfd4ab000 0x0 0x1000>,
-              <0x0 0xfd4ac000 0x0 0x1000>;
+        reg = <0xfd4a0000 0x1000>,
+              <0xfd4aa000 0x1000>,
+              <0xfd4ab000 0x1000>,
+              <0xfd4ac000 0x1000>;
         reg-names = "dp", "blend", "av_buf", "aud";
         interrupts = <0 119 4>;
         interrupt-parent = <&gic>;
diff --git a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml
index 5de510f..2a595b1 100644
--- a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml
+++ b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml
@@ -57,7 +57,7 @@
 
     dma: dma-controller@fd4c0000 {
       compatible = "xlnx,zynqmp-dpdma";
-      reg = <0x0 0xfd4c0000 0x0 0x1000>;
+      reg = <0xfd4c0000 0x1000>;
       interrupts = <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>;
       interrupt-parent = <&gic>;
       clocks = <&dpdma_clk>;
diff --git a/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml b/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml
index ccf5b50..dfa1133 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml
+++ b/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml
@@ -7,7 +7,7 @@
 title: Freescale MXS GPIO controller
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
   - Anson Huang <Anson.Huang@nxp.com>
 
 description: |
diff --git a/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt b/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt
index d4d8391..be329ea4 100644
--- a/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt
+++ b/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt
@@ -20,8 +20,9 @@
 - gpio-controller : Marks the device node as a GPIO controller
 - interrupts : Interrupt specifier, see interrupt-controller/interrupts.txt
 - interrupt-controller : Mark the GPIO controller as an interrupt-controller
-- ngpios : number of GPIO lines, see gpio.txt
-  (should be multiple of 8, up to 80 pins)
+- ngpios : number of *hardware* GPIO lines, see gpio.txt. This will expose
+  2 software GPIOs per hardware GPIO: one for hardware input, one for hardware
+  output. Up to 80 pins, must be a multiple of 8.
 - clocks : A phandle to the APB clock for SGPM clock division
 - bus-frequency : SGPM CLK frequency
 
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml
index d3134ed..21ae7bc 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml
+++ b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml
@@ -7,7 +7,7 @@
 title: Freescale MXS Inter IC (I2C) Controller
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt
deleted file mode 100644
index 7841cb0..0000000
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt
+++ /dev/null
@@ -1,66 +0,0 @@
-Texas Instruments K3 Interrupt Aggregator
-=========================================
-
-The Interrupt Aggregator (INTA) provides a centralized machine
-which handles the termination of system events to that they can
-be coherently processed by the host(s) in the system. A maximum
-of 64 events can be mapped to a single interrupt.
-
-
-                              Interrupt Aggregator
-                     +-----------------------------------------+
-                     |      Intmap            VINT             |
-                     | +--------------+  +------------+        |
-            m ------>| | vint  | bit  |  | 0 |.....|63| vint0  |
-               .     | +--------------+  +------------+        |       +------+
-               .     |         .               .               |       | HOST |
-Globalevents  ------>|         .               .               |------>| IRQ  |
-               .     |         .               .               |       | CTRL |
-               .     |         .               .               |       +------+
-            n ------>| +--------------+  +------------+        |
-                     | | vint  | bit  |  | 0 |.....|63| vintx  |
-                     | +--------------+  +------------+        |
-                     |                                         |
-                     +-----------------------------------------+
-
-Configuration of these Intmap registers that maps global events to vint is done
-by a system controller (like the Device Memory and Security Controller on K3
-AM654 SoC). Driver should request the system controller to get the range
-of global events and vints assigned to the requesting host. Management
-of these requested resources should be handled by driver and requests
-system controller to map specific global event to vint, bit pair.
-
-Communication between the host processor running an OS and the system
-controller happens through a protocol called TI System Control Interface
-(TISCI protocol). For more details refer:
-Documentation/devicetree/bindings/arm/keystone/ti,sci.txt
-
-TISCI Interrupt Aggregator Node:
--------------------------------
-- compatible:		Must be "ti,sci-inta".
-- reg:			Should contain registers location and length.
-- interrupt-controller:	Identifies the node as an interrupt controller
-- msi-controller:	Identifies the node as an MSI controller.
-- interrupt-parent:	phandle of irq parent.
-- ti,sci:		Phandle to TI-SCI compatible System controller node.
-- ti,sci-dev-id:	TISCI device ID of the Interrupt Aggregator.
-- ti,sci-rm-range-vint:	Array of TISCI subtype ids representing vints(inta
-			outputs) range within this INTA, assigned to the
-			requesting host context.
-- ti,sci-rm-range-global-event:	Array of TISCI subtype ids representing the
-			global events range reaching this IA and are assigned
-			to the requesting host context.
-
-Example:
---------
-main_udmass_inta: interrupt-controller@33d00000 {
-	compatible = "ti,sci-inta";
-	reg = <0x0 0x33d00000 0x0 0x100000>;
-	interrupt-controller;
-	msi-controller;
-	interrupt-parent = <&main_navss_intr>;
-	ti,sci = <&dmsc>;
-	ti,sci-dev-id = <179>;
-	ti,sci-rm-range-vint = <0x0>;
-	ti,sci-rm-range-global-event = <0x1>;
-};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
new file mode 100644
index 0000000..c7cd056
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
@@ -0,0 +1,98 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interrupt-controller/ti,sci-inta.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments K3 Interrupt Aggregator
+
+maintainers:
+  - Lokesh Vutla <lokeshvutla@ti.com>
+
+allOf:
+  - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml#
+
+description: |
+  The Interrupt Aggregator (INTA) provides a centralized machine
+  which handles the termination of system events to that they can
+  be coherently processed by the host(s) in the system. A maximum
+  of 64 events can be mapped to a single interrupt.
+
+                                Interrupt Aggregator
+                       +-----------------------------------------+
+                       |      Intmap            VINT             |
+                       | +--------------+  +------------+        |
+              m ------>| | vint  | bit  |  | 0 |.....|63| vint0  |
+                 .     | +--------------+  +------------+        |      +------+
+                 .     |         .               .               |      | HOST |
+  Globalevents  ------>|         .               .               |----->| IRQ  |
+                 .     |         .               .               |      | CTRL |
+                 .     |         .               .               |      +------+
+              n ------>| +--------------+  +------------+        |
+                       | | vint  | bit  |  | 0 |.....|63| vintx  |
+                       | +--------------+  +------------+        |
+                       |                                         |
+                       +-----------------------------------------+
+
+  Configuration of these Intmap registers that maps global events to vint is
+  done by a system controller (like the Device Memory and Security Controller
+  on AM654 SoC). Driver should request the system controller to get the range
+  of global events and vints assigned to the requesting host. Management
+  of these requested resources should be handled by driver and requests
+  system controller to map specific global event to vint, bit pair.
+
+  Communication between the host processor running an OS and the system
+  controller happens through a protocol called TI System Control Interface
+  (TISCI protocol).
+
+properties:
+  compatible:
+    const: ti,sci-inta
+
+  reg:
+    maxItems: 1
+
+  interrupt-controller: true
+
+  msi-controller: true
+
+  ti,interrupt-ranges:
+    $ref: /schemas/types.yaml#/definitions/uint32-matrix
+    description: |
+      Interrupt ranges that converts the INTA output hw irq numbers
+      to parents's input interrupt numbers.
+    items:
+      items:
+        - description: |
+            "output_irq" specifies the base for inta output irq
+        - description: |
+            "parent's input irq" specifies the base for parent irq
+        - description: |
+            "limit" specifies the limit for translation
+
+required:
+  - compatible
+  - reg
+  - interrupt-controller
+  - msi-controller
+  - ti,sci
+  - ti,sci-dev-id
+  - ti,interrupt-ranges
+
+examples:
+  - |
+    bus {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        main_udmass_inta: msi-controller@33d00000 {
+            compatible = "ti,sci-inta";
+            reg = <0x0 0x33d00000 0x0 0x100000>;
+            interrupt-controller;
+            msi-controller;
+            interrupt-parent = <&main_navss_intr>;
+            ti,sci = <&dmsc>;
+            ti,sci-dev-id = <179>;
+            ti,interrupt-ranges = <0 0 256>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt
deleted file mode 100644
index 178fca0..0000000
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt
+++ /dev/null
@@ -1,82 +0,0 @@
-Texas Instruments K3 Interrupt Router
-=====================================
-
-The Interrupt Router (INTR) module provides a mechanism to mux M
-interrupt inputs to N interrupt outputs, where all M inputs are selectable
-to be driven per N output. An Interrupt Router can either handle edge triggered
-or level triggered interrupts and that is fixed in hardware.
-
-                                 Interrupt Router
-                             +----------------------+
-                             |  Inputs     Outputs  |
-        +-------+            | +------+    +-----+  |
-        | GPIO  |----------->| | irq0 |    |  0  |  |       Host IRQ
-        +-------+            | +------+    +-----+  |      controller
-                             |    .           .     |      +-------+
-        +-------+            |    .           .     |----->|  IRQ  |
-        | INTA  |----------->|    .           .     |      +-------+
-        +-------+            |    .        +-----+  |
-                             | +------+    |  N  |  |
-                             | | irqM |    +-----+  |
-                             | +------+             |
-                             |                      |
-                             +----------------------+
-
-There is one register per output (MUXCNTL_N) that controls the selection.
-Configuration of these MUXCNTL_N registers is done by a system controller
-(like the Device Memory and Security Controller on K3 AM654 SoC). System
-controller will keep track of the used and unused registers within the Router.
-Driver should request the system controller to get the range of GIC IRQs
-assigned to the requesting hosts. It is the drivers responsibility to keep
-track of Host IRQs.
-
-Communication between the host processor running an OS and the system
-controller happens through a protocol called TI System Control Interface
-(TISCI protocol). For more details refer:
-Documentation/devicetree/bindings/arm/keystone/ti,sci.txt
-
-TISCI Interrupt Router Node:
-----------------------------
-Required Properties:
-- compatible:		Must be "ti,sci-intr".
-- ti,intr-trigger-type:	Should be one of the following:
-			1: If intr supports edge triggered interrupts.
-			4: If intr supports level triggered interrupts.
-- interrupt-controller:	Identifies the node as an interrupt controller
-- #interrupt-cells:	Specifies the number of cells needed to encode an
-			interrupt source. The value should be 2.
-			First cell should contain the TISCI device ID of source
-			Second cell should contain the interrupt source offset
-			within the device.
-- ti,sci:		Phandle to TI-SCI compatible System controller node.
-- ti,sci-dst-id:	TISCI device ID of the destination IRQ controller.
-- ti,sci-rm-range-girq:	Array of TISCI subtype ids representing the host irqs
-			assigned to this interrupt router. Each subtype id
-			corresponds to a range of host irqs.
-
-For more details on TISCI IRQ resource management refer:
-https://downloads.ti.com/tisci/esd/latest/2_tisci_msgs/rm/rm_irq.html
-
-Example:
---------
-The following example demonstrates both interrupt router node and the consumer
-node(main gpio) on the AM654 SoC:
-
-main_intr: interrupt-controller0 {
-	compatible = "ti,sci-intr";
-	ti,intr-trigger-type = <1>;
-	interrupt-controller;
-	interrupt-parent = <&gic500>;
-	#interrupt-cells = <2>;
-	ti,sci = <&dmsc>;
-	ti,sci-dst-id = <56>;
-	ti,sci-rm-range-girq = <0x1>;
-};
-
-main_gpio0: gpio@600000 {
-	...
-	interrupt-parent = <&main_intr>;
-	interrupts = <57 256>, <57 257>, <57 258>,
-		     <57 259>, <57 260>, <57 261>;
-	...
-};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml
new file mode 100644
index 0000000..cff6a95
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml
@@ -0,0 +1,102 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interrupt-controller/ti,sci-intr.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments K3 Interrupt Router
+
+maintainers:
+  - Lokesh Vutla <lokeshvutla@ti.com>
+
+allOf:
+  - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml#
+
+description: |
+  The Interrupt Router (INTR) module provides a mechanism to mux M
+  interrupt inputs to N interrupt outputs, where all M inputs are selectable
+  to be driven per N output. An Interrupt Router can either handle edge
+  triggered or level triggered interrupts and that is fixed in hardware.
+
+                                   Interrupt Router
+                               +----------------------+
+                               |  Inputs     Outputs  |
+          +-------+            | +------+    +-----+  |
+          | GPIO  |----------->| | irq0 |    |  0  |  |       Host IRQ
+          +-------+            | +------+    +-----+  |      controller
+                               |    .           .     |      +-------+
+          +-------+            |    .           .     |----->|  IRQ  |
+          | INTA  |----------->|    .           .     |      +-------+
+          +-------+            |    .        +-----+  |
+                               | +------+    |  N  |  |
+                               | | irqM |    +-----+  |
+                               | +------+             |
+                               |                      |
+                               +----------------------+
+
+  There is one register per output (MUXCNTL_N) that controls the selection.
+  Configuration of these MUXCNTL_N registers is done by a system controller
+  (like the Device Memory and Security Controller on K3 AM654 SoC). System
+  controller will keep track of the used and unused registers within the Router.
+  Driver should request the system controller to get the range of GIC IRQs
+  assigned to the requesting hosts. It is the drivers responsibility to keep
+  track of Host IRQs.
+
+  Communication between the host processor running an OS and the system
+  controller happens through a protocol called TI System Control Interface
+  (TISCI protocol).
+
+properties:
+  compatible:
+    const: ti,sci-intr
+
+  ti,intr-trigger-type:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [1, 4]
+    description: |
+      Should be one of the following.
+        1 = If intr supports edge triggered interrupts.
+        4 = If intr supports level triggered interrupts.
+
+  interrupt-controller: true
+
+  '#interrupt-cells':
+    const: 1
+    description: |
+      The 1st cell should contain interrupt router input hw number.
+
+  ti,interrupt-ranges:
+    $ref: /schemas/types.yaml#/definitions/uint32-matrix
+    description: |
+      Interrupt ranges that converts the INTR output hw irq numbers
+      to parents's input interrupt numbers.
+    items:
+      items:
+        - description: |
+            "output_irq" specifies the base for intr output irq
+        - description: |
+            "parent's input irq" specifies the base for parent irq
+        - description: |
+            "limit" specifies the limit for translation
+
+required:
+  - compatible
+  - ti,intr-trigger-type
+  - interrupt-controller
+  - '#interrupt-cells'
+  - ti,sci
+  - ti,sci-dev-id
+  - ti,interrupt-ranges
+
+examples:
+  - |
+    main_gpio_intr: interrupt-controller0 {
+        compatible = "ti,sci-intr";
+        ti,intr-trigger-type = <1>;
+        interrupt-controller;
+        interrupt-parent = <&gic500>;
+        #interrupt-cells = <1>;
+        ti,sci = <&dmsc>;
+        ti,sci-dev-id = <131>;
+        ti,interrupt-ranges = <0 360 32>;
+    };
diff --git a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml
index 24ad144..fe7fa25 100644
--- a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml
+++ b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml
@@ -30,7 +30,7 @@
     const: 0
 
 patternProperties:
-  "^multi-led[0-9a-f]$":
+  "^multi-led@[0-9a-b]$":
     type: object
     allOf:
       - $ref: leds-class-multicolor.yaml#
diff --git a/Documentation/devicetree/bindings/media/i2c/imx274.txt b/Documentation/devicetree/bindings/media/i2c/imx274.txt
deleted file mode 100644
index 0727079..0000000
--- a/Documentation/devicetree/bindings/media/i2c/imx274.txt
+++ /dev/null
@@ -1,38 +0,0 @@
-* Sony 1/2.5-Inch 8.51Mp CMOS Digital Image Sensor
-
-The Sony imx274 is a 1/2.5-inch CMOS active pixel digital image sensor with
-an active array size of 3864H x 2202V. It is programmable through I2C
-interface. The I2C address is fixed to 0x1a as per sensor data sheet.
-Image data is sent through MIPI CSI-2, which is configured as 4 lanes
-at 1440 Mbps.
-
-
-Required Properties:
-- compatible: value should be "sony,imx274" for imx274 sensor
-- reg: I2C bus address of the device
-
-Optional Properties:
-- reset-gpios: Sensor reset GPIO
-- clocks: Reference to the input clock.
-- clock-names: Should be "inck".
-- VANA-supply: Sensor 2.8v analog supply.
-- VDIG-supply: Sensor 1.8v digital core supply.
-- VDDL-supply: Sensor digital IO 1.2v supply.
-
-The imx274 device node should contain one 'port' child node with
-an 'endpoint' subnode. For further reading on port node refer to
-Documentation/devicetree/bindings/media/video-interfaces.txt.
-
-Example:
-	sensor@1a {
-		compatible = "sony,imx274";
-		reg = <0x1a>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		reset-gpios = <&gpio_sensor 0 0>;
-		port {
-			sensor_out: endpoint {
-				remote-endpoint = <&csiss_in>;
-			};
-		};
-	};
diff --git a/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml b/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
new file mode 100644
index 0000000..f697e1a
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/i2c/sony,imx274.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Sony 1/2.5-Inch 8.51MP CMOS Digital Image Sensor
+
+maintainers:
+  - Leon Luo <leonl@leopardimaging.com>
+
+description: |
+  The Sony IMX274 is a 1/2.5-inch CMOS active pixel digital image sensor with an
+  active array size of 3864H x 2202V. It is programmable through I2C interface.
+  Image data is sent through MIPI CSI-2, which is configured as 4 lanes at 1440
+  Mbps.
+
+properties:
+  compatible:
+    const: sony,imx274
+
+  reg:
+    const: 0x1a
+
+  reset-gpios:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    const: inck
+
+  vana-supply:
+    description: Sensor 2.8 V analog supply.
+    maxItems: 1
+
+  vdig-supply:
+    description: Sensor 1.8 V digital core supply.
+    maxItems: 1
+
+  vddl-supply:
+    description: Sensor digital IO 1.2 V supply.
+    maxItems: 1
+
+  port:
+    type: object
+    description: Output video port. See ../video-interfaces.txt.
+
+required:
+  - compatible
+  - reg
+  - port
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c0 {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        imx274: camera-sensor@1a {
+            compatible = "sony,imx274";
+            reg = <0x1a>;
+            reset-gpios = <&gpio_sensor 0 0>;
+
+            port {
+                sensor_out: endpoint {
+                    remote-endpoint = <&csiss_in>;
+                };
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml b/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml
index 5887c91..58fe9d0 100644
--- a/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml
+++ b/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml
@@ -30,9 +30,13 @@
     then:
       properties:
         clock-output-names:
-          items:
-            - const: clk_out_sd0
-            - const: clk_in_sd0
+          oneOf:
+            - items:
+              - const: clk_out_sd0
+              - const: clk_in_sd0
+            - items:
+              - const: clk_out_sd1
+              - const: clk_in_sd1
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml
index 75dc116..10b4596 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml
+++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml
@@ -7,7 +7,7 @@
 title: Freescale Enhanced Secure Digital Host Controller (eSDHC) for i.MX
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 allOf:
   - $ref: "mmc-controller.yaml"
diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.txt b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
index 0c9cf6a..26a8f32 100644
--- a/Documentation/devicetree/bindings/mmc/mtk-sd.txt
+++ b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
@@ -50,6 +50,8 @@
 		     error caused by stop clock(fifo full)
 		     Valid range = [0:0x7]. if not present, default value is 0.
 		     applied to compatible "mediatek,mt2701-mmc".
+- resets: Phandle and reset specifier pair to softreset line of MSDC IP.
+- reset-names: Should be "hrst".
 
 Examples:
 mmc0: mmc@11230000 {
diff --git a/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml b/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml
index 1cccc04..bec8f8c 100644
--- a/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml
+++ b/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml
@@ -7,7 +7,7 @@
 title: Freescale MXS MMC controller
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 description: |
   The Freescale MXS Synchronous Serial Ports (SSP) can act as a MMC controller
diff --git a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt
index 2cf3aff..96c0b14 100644
--- a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt
@@ -15,8 +15,15 @@
   - "nvidia,tegra210-sdhci": for Tegra210
   - "nvidia,tegra186-sdhci": for Tegra186
   - "nvidia,tegra194-sdhci": for Tegra194
-- clocks : Must contain one entry, for the module clock.
-  See ../clocks/clock-bindings.txt for details.
+- clocks: For Tegra210, Tegra186 and Tegra194 must contain two entries.
+	  One for the module clock and one for the timeout clock.
+	  For all other Tegra devices, must contain a single entry for
+	  the module clock. See ../clocks/clock-bindings.txt for details.
+- clock-names: For Tegra210, Tegra186 and Tegra194 must contain the
+	       strings 'sdhci' and 'tmclk' to represent the module and
+	       the timeout clocks, respectively.
+	       For all other Tegra devices must contain the string 'sdhci'
+	       to represent the module clock.
 - resets : Must contain an entry for each entry in reset-names.
   See ../reset/reset.txt for details.
 - reset-names : Must include the following entries:
@@ -99,7 +106,7 @@
 
 Example:
 sdhci@700b0000 {
-	compatible = "nvidia,tegra210-sdhci", "nvidia,tegra124-sdhci";
+	compatible = "nvidia,tegra124-sdhci";
 	reg = <0x0 0x700b0000 0x0 0x200>;
 	interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
 	clocks = <&tegra_car TEGRA210_CLK_SDMMC1>;
@@ -115,3 +122,22 @@
 	nvidia,pad-autocal-pull-down-offset-1v8 = <0x7b>;
 	status = "disabled";
 };
+
+sdhci@700b0000 {
+	compatible = "nvidia,tegra210-sdhci";
+	reg = <0x0 0x700b0000 0x0 0x200>;
+	interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&tegra_car TEGRA210_CLK_SDMMC1>,
+		 <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>;
+	clock-names = "sdhci", "tmclk";
+	resets = <&tegra_car 14>;
+	reset-names = "sdhci";
+	pinctrl-names = "sdmmc-3v3", "sdmmc-1v8";
+	pinctrl-0 = <&sdmmc1_3v3>;
+	pinctrl-1 = <&sdmmc1_1v8>;
+	nvidia,pad-autocal-pull-up-offset-3v3 = <0x00>;
+	nvidia,pad-autocal-pull-down-offset-3v3 = <0x7d>;
+	nvidia,pad-autocal-pull-up-offset-1v8 = <0x7b>;
+	nvidia,pad-autocal-pull-down-offset-1v8 = <0x7b>;
+	status = "disabled";
+};
diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt
index bf7328a..dab208b 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.txt
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt
@@ -1,4 +1,4 @@
 Distributed Switch Architecture Device Tree Bindings
 ----------------------------------------------------
 
-See Documentation/devicetree/bindings/net/dsa/dsa.yaml for the documenation.
+See Documentation/devicetree/bindings/net/dsa/dsa.yaml for the documentation.
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 1c44740..fa2baca 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -54,7 +54,8 @@
 
   phy-connection-type:
     description:
-      Operation mode of the PHY interface
+      Specifies interface type between the Ethernet device and a physical
+      layer (PHY) device.
     enum:
       # There is not a standard bus between the MAC and the PHY,
       # something proprietary is being used to embed the PHY in the
diff --git a/Documentation/devicetree/bindings/net/renesas,ether.yaml b/Documentation/devicetree/bindings/net/renesas,ether.yaml
index 08678af..8ce5ed8 100644
--- a/Documentation/devicetree/bindings/net/renesas,ether.yaml
+++ b/Documentation/devicetree/bindings/net/renesas,ether.yaml
@@ -59,9 +59,15 @@
   clocks:
     maxItems: 1
 
-  pinctrl-0: true
+  power-domains:
+    maxItems: 1
 
-  pinctrl-names: true
+  resets:
+    maxItems: 1
+
+  phy-mode: true
+
+  phy-handle: true
 
   renesas,no-ether-link:
     type: boolean
@@ -74,6 +80,11 @@
       specify when the Ether LINK signal is active-low instead of normal
       active-high
 
+patternProperties:
+  "^ethernet-phy@[0-9a-f]$":
+    type: object
+    $ref: ethernet-phy.yaml#
+
 required:
   - compatible
   - reg
@@ -83,7 +94,8 @@
   - '#address-cells'
   - '#size-cells'
   - clocks
-  - pinctrl-0
+
+additionalProperties: false
 
 examples:
   # Lager board
@@ -99,8 +111,6 @@
         clocks = <&mstp8_clks R8A7790_CLK_ETHER>;
         phy-mode = "rmii";
         phy-handle = <&phy1>;
-        pinctrl-0 = <&ether_pins>;
-        pinctrl-names = "default";
         renesas,ether-link-active-low;
         #address-cells = <1>;
         #size-cells = <0>;
@@ -109,7 +119,5 @@
             reg = <1>;
             interrupt-parent = <&irqc0>;
             interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
-            pinctrl-0 = <&phy1_pins>;
-            pinctrl-names = "default";
         };
     };
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index 032b76f..9119f1c 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -21,6 +21,7 @@
       - "renesas,etheravb-r8a774a1" for the R8A774A1 SoC.
       - "renesas,etheravb-r8a774b1" for the R8A774B1 SoC.
       - "renesas,etheravb-r8a774c0" for the R8A774C0 SoC.
+      - "renesas,etheravb-r8a774e1" for the R8A774E1 SoC.
       - "renesas,etheravb-r8a7795" for the R8A7795 SoC.
       - "renesas,etheravb-r8a7796" for the R8A77960 SoC.
       - "renesas,etheravb-r8a77961" for the R8A77961 SoC.
diff --git a/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml
index 64b2c64..a1e2be7 100644
--- a/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml
@@ -9,6 +9,14 @@
 maintainers:
   - Dilip Kota <eswara.kota@linux.intel.com>
 
+select:
+  properties:
+    compatible:
+      contains:
+        const: intel,lgm-pcie
+  required:
+    - compatible
+
 properties:
   compatible:
     items:
diff --git a/Documentation/devicetree/bindings/perf/arm,cmn.yaml b/Documentation/devicetree/bindings/perf/arm,cmn.yaml
new file mode 100644
index 0000000..e4fcc0d
--- /dev/null
+++ b/Documentation/devicetree/bindings/perf/arm,cmn.yaml
@@ -0,0 +1,57 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright 2020 Arm Ltd.
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/perf/arm,cmn.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Arm CMN (Coherent Mesh Network) Performance Monitors
+
+maintainers:
+  - Robin Murphy <robin.murphy@arm.com>
+
+properties:
+  compatible:
+    const: arm,cmn-600
+
+  reg:
+    items:
+      - description: Physical address of the base (PERIPHBASE) and
+          size (up to 64MB) of the configuration address space.
+
+  interrupts:
+    minItems: 1
+    maxItems: 4
+    items:
+      - description: Overflow interrupt for DTC0
+      - description: Overflow interrupt for DTC1
+      - description: Overflow interrupt for DTC2
+      - description: Overflow interrupt for DTC3
+    description: One interrupt for each DTC domain implemented must
+      be specified, in order. DTC0 is always present.
+
+  arm,root-node:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: Offset from PERIPHBASE of the configuration
+      discovery node (see TRM definition of ROOTNODEBASE).
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - arm,root-node
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    pmu@50000000 {
+        compatible = "arm,cmn-600";
+        reg = <0x50000000 0x4000000>;
+        /* 4x2 mesh with one DTC, and CFG node at 0,1,1,0 */
+        interrupts = <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>;
+        arm,root-node = <0x104000>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml b/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml
index da68f4a..8740e07 100644
--- a/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml
+++ b/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml
@@ -7,7 +7,7 @@
 title: Freescale MXS PWM controller
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
   - Anson Huang <anson.huang@nxp.com>
 
 properties:
diff --git a/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt b/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
index f5e518d..62d4ed2 100644
--- a/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
+++ b/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
@@ -23,8 +23,8 @@
 
 - compatible:
     Must be one of :
-    "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-qspi" : MSPI+BSPI on BRCMSTB SoCs
-    "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
+    "brcm,spi-brcmstb-qspi", "brcm,spi-bcm-qspi" : MSPI+BSPI on BRCMSTB SoCs
+    "brcm,spi-brcmstb-mspi", "brcm,spi-bcm-qspi" : Second Instance of MSPI
 						   BRCMSTB  SoCs
     "brcm,spi-bcm7425-qspi", "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
     			     			  			    BRCMSTB  SoCs
@@ -36,8 +36,8 @@
     			     			  			    BRCMSTB  SoCs
     "brcm,spi-bcm7278-qspi", "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
     			     			  			    BRCMSTB  SoCs
-    "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi"     : MSPI+BSPI on Cygnus, NSP
-    "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi"     : NS2 SoCs
+    "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi"     : MSPI+BSPI on Cygnus, NSP
+    "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi"     : NS2 SoCs
 
 - reg:
     Define the bases and ranges of the associated I/O address spaces.
@@ -86,7 +86,7 @@
     spi@f03e3400 {
 		#address-cells = <0x1>;
 		#size-cells = <0x0>;
-		compatible = "brcm,spi-brcmstb-qspi", "brcm,spi-brcmstb-qspi";
+		compatible = "brcm,spi-brcmstb-qspi", "brcm,spi-bcm-qspi";
 		reg = <0xf03e0920 0x4 0xf03e3400 0x188 0xf03e3200 0x50>;
 		reg-names = "cs_reg", "mspi", "bspi";
 		interrupts = <0x6 0x5 0x4 0x3 0x2 0x1 0x0>;
@@ -149,7 +149,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clocks = <&upg_fixed>;
-		compatible = "brcm,spi-brcmstb-qspi", "brcm,spi-brcmstb-mspi";
+		compatible = "brcm,spi-brcmstb-mspi", "brcm,spi-bcm-qspi";
 		reg = <0xf0416000 0x180>;
 		reg-names = "mspi";
 		interrupts = <0x14>;
@@ -160,7 +160,7 @@
 iProc SoC Example:
 
     qspi: spi@18027200 {
-	compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+	compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 	reg = <0x18027200 0x184>,
 	      <0x18027000 0x124>,
 	      <0x1811c408 0x004>,
@@ -191,7 +191,7 @@
  NS2 SoC Example:
 
 	       qspi: spi@66470200 {
-		       compatible = "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi";
+		       compatible = "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi";
 		       reg = <0x66470200 0x184>,
 			     <0x66470000 0x124>,
 			     <0x67017408 0x004>,
diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml
index 1b50ced..50df1a4 100644
--- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml
+++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml
@@ -7,7 +7,7 @@
 title: Freescale (Enhanced) Configurable Serial Peripheral Interface (CSPI/eCSPI) for i.MX
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
 
 allOf:
   - $ref: "/schemas/spi/spi-controller.yaml#"
diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
index 22882e7..312d8fe 100644
--- a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
@@ -39,6 +39,7 @@
       spi common code does not support use of CS signals discontinuously.
       i.MX8DXL-EVK board only uses CS1 without using CS0. Therefore, add
       this property to re-config the chipselect value in the LPSPI driver.
+    type: boolean
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml
index aedac16..16b57f5 100644
--- a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml
+++ b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml
@@ -7,7 +7,7 @@
 title: NXP i.MX Thermal Binding
 
 maintainers:
-  - Shawn Guo <shawn.guo@linaro.org>
+  - Shawn Guo <shawnguo@kernel.org>
   - Anson Huang <Anson.Huang@nxp.com>
 
 properties:
diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
new file mode 100644
index 0000000..2a0e9cd
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
@@ -0,0 +1,60 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/timer/sifive,clint.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: SiFive Core Local Interruptor
+
+maintainers:
+  - Palmer Dabbelt <palmer@dabbelt.com>
+  - Anup Patel <anup.patel@wdc.com>
+
+description:
+  SiFive (and other RISC-V) SOCs include an implementation of the SiFive
+  Core Local Interruptor (CLINT) for M-mode timer and M-mode inter-processor
+  interrupts. It directly connects to the timer and inter-processor interrupt
+  lines of various HARTs (or CPUs) so RISC-V per-HART (or per-CPU) local
+  interrupt controller is the parent interrupt controller for CLINT device.
+  The clock frequency of CLINT is specified via "timebase-frequency" DT
+  property of "/cpus" DT node. The "timebase-frequency" DT property is
+  described in Documentation/devicetree/bindings/riscv/cpus.yaml
+
+properties:
+  compatible:
+    items:
+      - const: sifive,fu540-c000-clint
+      - const: sifive,clint0
+
+    description:
+      Should be "sifive,<chip>-clint" and "sifive,clint<version>".
+      Supported compatible strings are -
+      "sifive,fu540-c000-clint" for the SiFive CLINT v0 as integrated
+      onto the SiFive FU540 chip, and "sifive,clint0" for the SiFive
+      CLINT v0 IP block with no chip integration tweaks.
+      Please refer to sifive-blocks-ip-versioning.txt for details
+
+  reg:
+    maxItems: 1
+
+  interrupts-extended:
+    minItems: 1
+
+additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts-extended
+
+examples:
+  - |
+    timer@2000000 {
+      compatible = "sifive,fu540-c000-clint", "sifive,clint0";
+      interrupts-extended = <&cpu1intc 3 &cpu1intc 7
+                             &cpu2intc 3 &cpu2intc 7
+                             &cpu3intc 3 &cpu3intc 7
+                             &cpu4intc 3 &cpu4intc 7>;
+       reg = <0x2000000 0x10000>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml
index 4ace803..25c4239 100644
--- a/Documentation/devicetree/bindings/trivial-devices.yaml
+++ b/Documentation/devicetree/bindings/trivial-devices.yaml
@@ -326,6 +326,8 @@
           - silabs,si7020
             # Skyworks SKY81452: Six-Channel White LED Driver with Touch Panel Bias Supply
           - skyworks,sky81452
+            # Socionext SynQuacer TPM MMIO module
+          - socionext,synquacer-tpm-mmio
             # i2c serial eeprom  (24cxx)
           - st,24c256
             # Ambient Light Sensor with SMBUS/Two Wire Serial Interface
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 2baee2c..63996ab 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -993,7 +993,7 @@
   "^sst,.*":
     description: Silicon Storage Technology, Inc.
   "^sstar,.*":
-    description: Xiamen Xingchen(SigmaStar) Technology Co., Ltd. 
+    description: Xiamen Xingchen(SigmaStar) Technology Co., Ltd.
       (formerly part of MStar Semiconductor, Inc.)
   "^st,.*":
     description: STMicroelectronics
diff --git a/Documentation/devicetree/writing-schema.rst b/Documentation/devicetree/writing-schema.rst
index 8c74a99..16f21e18 100644
--- a/Documentation/devicetree/writing-schema.rst
+++ b/Documentation/devicetree/writing-schema.rst
@@ -5,7 +5,7 @@
 
 Devicetree bindings are written using json-schema vocabulary. Schema files are
 written in a JSON compatible subset of YAML. YAML is used instead of JSON as it
-considered more human readable and has some advantages such as allowing
+is considered more human readable and has some advantages such as allowing
 comments (Prefixed with '#').
 
 Schema Contents
@@ -19,7 +19,7 @@
   A json-schema unique identifier string. The string must be a valid
   URI typically containing the binding's filename and path. For DT schema, it must
   begin with "http://devicetree.org/schemas/". The URL is used in constructing
-  references to other files specified in schema "$ref" properties. A $ref values
+  references to other files specified in schema "$ref" properties. A $ref value
   with a leading '/' will have the hostname prepended. A $ref value a relative
   path or filename only will be prepended with the hostname and path components
   of the current schema file's '$id' value. A URL is used even for local files,
diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index 100bfd2..13ea0cc 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -179,7 +179,7 @@
    :internal:
 
 Indefinite DMA Fences
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~
 
 At various times &dma_fence with an indefinite time until dma_fence_wait()
 finishes have been proposed. Examples include:
diff --git a/Documentation/driver-api/fpga/fpga-bridge.rst b/Documentation/driver-api/fpga/fpga-bridge.rst
index 71c5a40..ccd677b 100644
--- a/Documentation/driver-api/fpga/fpga-bridge.rst
+++ b/Documentation/driver-api/fpga/fpga-bridge.rst
@@ -6,9 +6,9 @@
 
 * struct :c:type:`fpga_bridge` — The FPGA Bridge structure
 * struct :c:type:`fpga_bridge_ops` — Low level Bridge driver ops
-* :c:func:`devm_fpga_bridge_create()` — Allocate and init a bridge struct
-* :c:func:`fpga_bridge_register()` — Register a bridge
-* :c:func:`fpga_bridge_unregister()` — Unregister a bridge
+* devm_fpga_bridge_create() — Allocate and init a bridge struct
+* fpga_bridge_register() — Register a bridge
+* fpga_bridge_unregister() — Unregister a bridge
 
 .. kernel-doc:: include/linux/fpga/fpga-bridge.h
    :functions: fpga_bridge
diff --git a/Documentation/driver-api/fpga/fpga-mgr.rst b/Documentation/driver-api/fpga/fpga-mgr.rst
index 576f194..af5382a 100644
--- a/Documentation/driver-api/fpga/fpga-mgr.rst
+++ b/Documentation/driver-api/fpga/fpga-mgr.rst
@@ -104,9 +104,9 @@
 * ``fpga_mgr_states`` —  Values for :c:member:`fpga_manager->state`.
 * struct :c:type:`fpga_manager` —  the FPGA manager struct
 * struct :c:type:`fpga_manager_ops` —  Low level FPGA manager driver ops
-* :c:func:`devm_fpga_mgr_create` —  Allocate and init a manager struct
-* :c:func:`fpga_mgr_register` —  Register an FPGA manager
-* :c:func:`fpga_mgr_unregister` —  Unregister an FPGA manager
+* devm_fpga_mgr_create() —  Allocate and init a manager struct
+* fpga_mgr_register() —  Register an FPGA manager
+* fpga_mgr_unregister() —  Unregister an FPGA manager
 
 .. kernel-doc:: include/linux/fpga/fpga-mgr.h
    :functions: fpga_mgr_states
diff --git a/Documentation/driver-api/fpga/fpga-programming.rst b/Documentation/driver-api/fpga/fpga-programming.rst
index b5484df..f487ad6 100644
--- a/Documentation/driver-api/fpga/fpga-programming.rst
+++ b/Documentation/driver-api/fpga/fpga-programming.rst
@@ -6,9 +6,9 @@
 
 The in-kernel API for FPGA programming is a combination of APIs from
 FPGA manager, bridge, and regions.  The actual function used to
-trigger FPGA programming is :c:func:`fpga_region_program_fpga()`.
+trigger FPGA programming is fpga_region_program_fpga().
 
-:c:func:`fpga_region_program_fpga()` uses functionality supplied by
+fpga_region_program_fpga() uses functionality supplied by
 the FPGA manager and bridges.  It will:
 
  * lock the region's mutex
@@ -20,8 +20,8 @@
  * release the locks
 
 The struct fpga_image_info specifies what FPGA image to program.  It is
-allocated/freed by :c:func:`fpga_image_info_alloc()` and freed with
-:c:func:`fpga_image_info_free()`
+allocated/freed by fpga_image_info_alloc() and freed with
+fpga_image_info_free()
 
 How to program an FPGA using a region
 -------------------------------------
@@ -84,10 +84,10 @@
 API for programming an FPGA
 ---------------------------
 
-* :c:func:`fpga_region_program_fpga` —  Program an FPGA
-* :c:type:`fpga_image_info` —  Specifies what FPGA image to program
-* :c:func:`fpga_image_info_alloc()` —  Allocate an FPGA image info struct
-* :c:func:`fpga_image_info_free()` —  Free an FPGA image info struct
+* fpga_region_program_fpga() —  Program an FPGA
+* fpga_image_info() —  Specifies what FPGA image to program
+* fpga_image_info_alloc() —  Allocate an FPGA image info struct
+* fpga_image_info_free() —  Free an FPGA image info struct
 
 .. kernel-doc:: drivers/fpga/fpga-region.c
    :functions: fpga_region_program_fpga
diff --git a/Documentation/driver-api/fpga/fpga-region.rst b/Documentation/driver-api/fpga/fpga-region.rst
index 0529b2d..31118a8 100644
--- a/Documentation/driver-api/fpga/fpga-region.rst
+++ b/Documentation/driver-api/fpga/fpga-region.rst
@@ -46,18 +46,18 @@
 ----------------------------
 
 * struct :c:type:`fpga_region` — The FPGA region struct
-* :c:func:`devm_fpga_region_create` — Allocate and init a region struct
-* :c:func:`fpga_region_register` —  Register an FPGA region
-* :c:func:`fpga_region_unregister` —  Unregister an FPGA region
+* devm_fpga_region_create() — Allocate and init a region struct
+* fpga_region_register() —  Register an FPGA region
+* fpga_region_unregister() —  Unregister an FPGA region
 
 The FPGA region's probe function will need to get a reference to the FPGA
 Manager it will be using to do the programming.  This usually would happen
 during the region's probe function.
 
-* :c:func:`fpga_mgr_get` — Get a reference to an FPGA manager, raise ref count
-* :c:func:`of_fpga_mgr_get` —  Get a reference to an FPGA manager, raise ref count,
+* fpga_mgr_get() — Get a reference to an FPGA manager, raise ref count
+* of_fpga_mgr_get() —  Get a reference to an FPGA manager, raise ref count,
   given a device node.
-* :c:func:`fpga_mgr_put` — Put an FPGA manager
+* fpga_mgr_put() — Put an FPGA manager
 
 The FPGA region will need to specify which bridges to control while programming
 the FPGA.  The region driver can build a list of bridges during probe time
@@ -66,11 +66,11 @@
 (:c:member:`fpga_region->get_bridges`).  The FPGA bridge framework supplies the
 following APIs to handle building or tearing down that list.
 
-* :c:func:`fpga_bridge_get_to_list` — Get a ref of an FPGA bridge, add it to a
+* fpga_bridge_get_to_list() — Get a ref of an FPGA bridge, add it to a
   list
-* :c:func:`of_fpga_bridge_get_to_list` — Get a ref of an FPGA bridge, add it to a
+* of_fpga_bridge_get_to_list() — Get a ref of an FPGA bridge, add it to a
   list, given a device node
-* :c:func:`fpga_bridges_put` — Given a list of bridges, put them
+* fpga_bridges_put() — Given a list of bridges, put them
 
 .. kernel-doc:: include/linux/fpga/fpga-region.h
    :functions: fpga_region
diff --git a/Documentation/driver-api/iio/core.rst b/Documentation/driver-api/iio/core.rst
index b0bc0c0..51b21e0 100644
--- a/Documentation/driver-api/iio/core.rst
+++ b/Documentation/driver-api/iio/core.rst
@@ -11,10 +11,10 @@
 ----------------------
 
 * struct :c:type:`iio_dev` - industrial I/O device
-* :c:func:`iio_device_alloc()` - allocate an :c:type:`iio_dev` from a driver
-* :c:func:`iio_device_free()` - free an :c:type:`iio_dev` from a driver
-* :c:func:`iio_device_register()` - register a device with the IIO subsystem
-* :c:func:`iio_device_unregister()` - unregister a device from the IIO
+* iio_device_alloc() - allocate an :c:type:`iio_dev` from a driver
+* iio_device_free() - free an :c:type:`iio_dev` from a driver
+* iio_device_register() - register a device with the IIO subsystem
+* iio_device_unregister() - unregister a device from the IIO
   subsystem
 
 An IIO device usually corresponds to a single hardware sensor and it
@@ -34,17 +34,17 @@
 
 At probe:
 
-1. Call :c:func:`iio_device_alloc()`, which allocates memory for an IIO device.
+1. Call iio_device_alloc(), which allocates memory for an IIO device.
 2. Initialize IIO device fields with driver specific information (e.g.
    device name, device channels).
-3. Call :c:func:`iio_device_register()`, this registers the device with the
+3. Call iio_device_register(), this registers the device with the
    IIO core. After this call the device is ready to accept requests from user
    space applications.
 
 At remove, we free the resources allocated in probe in reverse order:
 
-1. :c:func:`iio_device_unregister()`, unregister the device from the IIO core.
-2. :c:func:`iio_device_free()`, free the memory allocated for the IIO device.
+1. iio_device_unregister(), unregister the device from the IIO core.
+2. iio_device_free(), free the memory allocated for the IIO device.
 
 IIO device sysfs interface
 ==========================
diff --git a/Documentation/fault-injection/nvme-fault-injection.rst b/Documentation/fault-injection/nvme-fault-injection.rst
index cdb2e82..1d44278 100644
--- a/Documentation/fault-injection/nvme-fault-injection.rst
+++ b/Documentation/fault-injection/nvme-fault-injection.rst
@@ -3,7 +3,7 @@
 Linux's fault injection framework provides a systematic way to support
 error injection via debugfs in the /sys/kernel/debug directory. When
 enabled, the default NVME_SC_INVALID_OPCODE with no retry will be
-injected into the nvme_end_request. Users can change the default status
+injected into the nvme_try_complete_req. Users can change the default status
 code and no retry flag via the debugfs. The list of Generic Command
 Status can be found in include/linux/nvme.h
 
diff --git a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt
index 53da483..1c49723 100644
--- a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt
+++ b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt
@@ -22,7 +22,7 @@
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
-    |     powerpc: |  ok  |
+    |     powerpc: | TODO |
     |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: | TODO |
diff --git a/Documentation/filesystems/affs.rst b/Documentation/filesystems/affs.rst
index 7f1a40d..5776cbd 100644
--- a/Documentation/filesystems/affs.rst
+++ b/Documentation/filesystems/affs.rst
@@ -110,13 +110,15 @@
 
   - R maps to r for user, group and others. On directories, R implies x.
 
-  - If both W and D are allowed, w will be set.
+  - W maps to w.
 
   - E maps to x.
 
-  - H and P are always retained and ignored under Linux.
+  - D is ignored.
 
-  - A is always reset when a file is written to.
+  - H, S and P are always retained and ignored under Linux.
+
+  - A is cleared when a file is written to.
 
 User id and group id will be used unless set[gu]id are given as mount
 options. Since most of the Amiga file systems are single user systems
@@ -128,11 +130,13 @@
 
 The Linux rwxrwxrwx file mode is handled as follows:
 
-  - r permission will set R for user, group and others.
+  - r permission will allow R for user, group and others.
 
-  - w permission will set W and D for user, group and others.
+  - w permission will allow W for user, group and others.
 
-  - x permission of the user will set E for plain files.
+  - x permission of the user will allow E for plain files.
+
+  - D will be allowed for user, group and others.
 
   - All other flags (suid, sgid, ...) are ignored and will
     not be retained.
diff --git a/Documentation/filesystems/ext4/about.rst b/Documentation/filesystems/ext4/about.rst
index 0aadba0..cc76b57 100644
--- a/Documentation/filesystems/ext4/about.rst
+++ b/Documentation/filesystems/ext4/about.rst
@@ -39,6 +39,6 @@
 Other References
 ----------------
 
-Also see http://www.nongnu.org/ext2-doc/ for quite a collection of
+Also see https://www.nongnu.org/ext2-doc/ for quite a collection of
 information about ext2/3. Here's another old reference:
 http://wiki.osdev.org/Ext2
diff --git a/Documentation/hwmon/abituguru-datasheet.rst b/Documentation/hwmon/abituguru-datasheet.rst
index 6d5253e..0cd6147 100644
--- a/Documentation/hwmon/abituguru-datasheet.rst
+++ b/Documentation/hwmon/abituguru-datasheet.rst
@@ -68,7 +68,7 @@
 number of bytes data per sensor and contents/meaning of those bytes.
 
 Although both this document and the kernel driver have kept the sensor
-terminoligy for the addressing within a bank this is not 100% correct, in
+terminology for the addressing within a bank this is not 100% correct, in
 bank 0x24 for example the addressing within the bank selects a PWM output not
 a sensor.
 
@@ -155,7 +155,7 @@
 turned up which do not hold 0x08 at DATA within 250 reads after writing the
 bank address. With these versions this happens quite frequent, using larger
 timeouts doesn't help, they just go offline for a second or 2, doing some
-internal callibration or whatever. Your code should be prepared to handle
+internal calibration or whatever. Your code should be prepared to handle
 this and in case of no response in this specific case just goto sleep for a
 while and then retry.
 
@@ -331,6 +331,6 @@
 0-0x30 with the reading code used for the sensor banks (0x20-0x28) and this
 resulted in a _permanent_ reprogramming of the voltages, luckily I had the
 sensors part configured so that it would shutdown my system on any out of spec
-voltages which proprably safed my computer (after a reboot I managed to
+voltages which probably safed my computer (after a reboot I managed to
 immediately enter the bios and reload the defaults). This probably means that
 the read/write cycle for the non sensor part is different from the sensor part.
diff --git a/Documentation/hwmon/abituguru.rst b/Documentation/hwmon/abituguru.rst
index d8243c8..cfda60b 100644
--- a/Documentation/hwmon/abituguru.rst
+++ b/Documentation/hwmon/abituguru.rst
@@ -17,7 +17,7 @@
     Note:
 	The uGuru is a microcontroller with onboard firmware which programs
 	it to behave as a hwmon IC. There are many different revisions of the
-	firmware and thus effectivly many different revisions of the uGuru.
+	firmware and thus effectively many different revisions of the uGuru.
 	Below is an incomplete list with which revisions are used for which
 	Motherboards:
 
@@ -33,7 +33,7 @@
 	sensortype (Volt or Temp) for bank1 sensors, for revision 1 uGuru's
 	this does not always work. For these uGuru's the autodetection can
 	be overridden with the bank1_types module param. For all 3 known
-	revison 1 motherboards the correct use of this param is:
+	revision 1 motherboards the correct use of this param is:
 	bank1_types=1,1,0,0,0,0,0,2,0,0,0,0,2,0,0,1
 	You may also need to specify the fan_sensors option for these boards
 	fan_sensors=5
diff --git a/Documentation/hwmon/abituguru3.rst b/Documentation/hwmon/abituguru3.rst
index 514f11f..88046d8 100644
--- a/Documentation/hwmon/abituguru3.rst
+++ b/Documentation/hwmon/abituguru3.rst
@@ -13,7 +13,7 @@
     Note:
 	The uGuru is a microcontroller with onboard firmware which programs
 	it to behave as a hwmon IC. There are many different revisions of the
-	firmware and thus effectivly many different revisions of the uGuru.
+	firmware and thus effectively many different revisions of the uGuru.
 	Below is an incomplete list with which revisions are used for which
 	Motherboards:
 
@@ -24,7 +24,7 @@
 	- uGuru 3.0.0.0 ~ 3.0.x.x (AW8, AL8, AT8, NI8 SLI, AT8 32X, AN8 32X,
 	  AW9D-MAX)
 
-	The abituguru3 driver is only for revison 3.0.x.x motherboards,
+	The abituguru3 driver is only for revision 3.0.x.x motherboards,
 	this driver will not work on older motherboards. For older
 	motherboards use the abituguru (without the 3 !) driver.
 
diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst
index 2aac50b..dae90c2 100644
--- a/Documentation/kbuild/llvm.rst
+++ b/Documentation/kbuild/llvm.rst
@@ -23,8 +23,8 @@
 Clang
 -----
 
-The compiler used can be swapped out via `CC=` command line argument to `make`.
-`CC=` should be set when selecting a config and during a build.
+The compiler used can be swapped out via ``CC=`` command line argument to ``make``.
+``CC=`` should be set when selecting a config and during a build. ::
 
 	make CC=clang defconfig
 
@@ -34,33 +34,33 @@
 ---------------
 
 A single Clang compiler binary will typically contain all supported backends,
-which can help simplify cross compiling.
+which can help simplify cross compiling. ::
 
 	ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- make CC=clang
 
-`CROSS_COMPILE` is not used to prefix the Clang compiler binary, instead
-`CROSS_COMPILE` is used to set a command line flag: `--target <triple>`. For
-example:
+``CROSS_COMPILE`` is not used to prefix the Clang compiler binary, instead
+``CROSS_COMPILE`` is used to set a command line flag: ``--target=<triple>``. For
+example: ::
 
-	clang --target aarch64-linux-gnu foo.c
+	clang --target=aarch64-linux-gnu foo.c
 
 LLVM Utilities
 --------------
 
-LLVM has substitutes for GNU binutils utilities. Kbuild supports `LLVM=1`
-to enable them.
+LLVM has substitutes for GNU binutils utilities. Kbuild supports ``LLVM=1``
+to enable them. ::
 
 	make LLVM=1
 
-They can be enabled individually. The full list of the parameters:
+They can be enabled individually. The full list of the parameters: ::
 
-	make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \\
-	  OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-size \\
-	  READELF=llvm-readelf HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar \\
+	make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \
+	  OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-size \
+	  READELF=llvm-readelf HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar \
 	  HOSTLD=ld.lld
 
 Currently, the integrated assembler is disabled by default. You can pass
-`LLVM_IAS=1` to enable it.
+``LLVM_IAS=1`` to enable it.
 
 Getting Help
 ------------
diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst
index b81b891..58d513a 100644
--- a/Documentation/kbuild/makefiles.rst
+++ b/Documentation/kbuild/makefiles.rst
@@ -16,7 +16,7 @@
 	   --- 3.5 Library file goals - lib-y
 	   --- 3.6 Descending down in directories
 	   --- 3.7 Compilation flags
-	   --- 3.8 Command line dependency
+	   --- 3.8 <deleted>
 	   --- 3.9 Dependency tracking
 	   --- 3.10 Special Rules
 	   --- 3.11 $(CC) support functions
@@ -39,8 +39,8 @@
 
 	=== 7 Architecture Makefiles
 	   --- 7.1 Set variables to tweak the build to the architecture
-	   --- 7.2 Add prerequisites to archheaders:
-	   --- 7.3 Add prerequisites to archprepare:
+	   --- 7.2 Add prerequisites to archheaders
+	   --- 7.3 Add prerequisites to archprepare
 	   --- 7.4 List directories to visit when descending
 	   --- 7.5 Architecture-specific boot images
 	   --- 7.6 Building non-kbuild targets
@@ -129,7 +129,7 @@
 be used and if both a 'Makefile' and a 'Kbuild' file exists, then the 'Kbuild'
 file will be used.
 
-Section 3.1 "Goal definitions" is a quick intro, further chapters provide
+Section 3.1 "Goal definitions" is a quick intro; further chapters provide
 more details, with real examples.
 
 3.1 Goal definitions
@@ -965,7 +965,7 @@
 		KBUILD_LDFLAGS         := -m elf_s390
 
 	Note: ldflags-y can be used to further customise
-	the flags used. See chapter 3.7.
+	the flags used. See section 3.7.
 
     LDFLAGS_vmlinux
 	Options for $(LD) when linking vmlinux
@@ -1121,7 +1121,7 @@
 
 	In this example, the file target maketools will be processed
 	before descending down in the subdirectories.
-	See also chapter XXX-TODO that describe how kbuild supports
+	See also chapter XXX-TODO that describes how kbuild supports
 	generating offset header files.
 
 
@@ -1261,7 +1261,7 @@
 	always be built.
 	Assignments to $(targets) are without $(obj)/ prefix.
 	if_changed may be used in conjunction with custom commands as
-	defined in 6.8 "Custom kbuild commands".
+	defined in 7.8 "Custom kbuild commands".
 
 	Note: It is a typical mistake to forget the FORCE prerequisite.
 	Another common pitfall is that whitespace is sometimes
@@ -1411,7 +1411,7 @@
 	that may be shared between individual architectures.
 	The recommended approach how to use a generic header file is
 	to list the file in the Kbuild file.
-	See "7.2 generic-y" for further info on syntax etc.
+	See "8.2 generic-y" for further info on syntax etc.
 
 7.11 Post-link pass
 -------------------
@@ -1601,4 +1601,4 @@
 
 - Describe how kbuild supports shipped files with _shipped.
 - Generating offset header files.
-- Add more variables to section 7?
+- Add more variables to chapters 7 or 9?
diff --git a/Documentation/locking/locktypes.rst b/Documentation/locking/locktypes.rst
index 4cefed8..ddada4a 100644
--- a/Documentation/locking/locktypes.rst
+++ b/Documentation/locking/locktypes.rst
@@ -164,14 +164,14 @@
 On non-PREEMPT_RT kernels local_lock operations map to the preemption and
 interrupt disabling and enabling primitives:
 
- =========================== ======================
- local_lock(&llock)          preempt_disable()
- local_unlock(&llock)        preempt_enable()
- local_lock_irq(&llock)      local_irq_disable()
- local_unlock_irq(&llock)    local_irq_enable()
- local_lock_save(&llock)     local_irq_save()
- local_lock_restore(&llock)  local_irq_save()
- =========================== ======================
+ ===============================  ======================
+ local_lock(&llock)               preempt_disable()
+ local_unlock(&llock)             preempt_enable()
+ local_lock_irq(&llock)           local_irq_disable()
+ local_unlock_irq(&llock)         local_irq_enable()
+ local_lock_irqsave(&llock)       local_irq_save()
+ local_unlock_irqrestore(&llock)  local_irq_restore()
+ ===============================  ======================
 
 The named scope of local_lock has two advantages over the regular
 primitives:
@@ -353,14 +353,14 @@
   {
     local_irq_save(flags);    -> local_lock_irqsave(&local_lock_1, flags);
     func3();
-    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_1, flags);
+    local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock_1, flags);
   }
 
   func2()
   {
     local_irq_save(flags);    -> local_lock_irqsave(&local_lock_2, flags);
     func3();
-    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_2, flags);
+    local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock_2, flags);
   }
 
   func3()
@@ -379,14 +379,14 @@
   {
     local_irq_save(flags);    -> local_lock_irqsave(&local_lock, flags);
     func3();
-    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags);
+    local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock, flags);
   }
 
   func2()
   {
     local_irq_save(flags);    -> local_lock_irqsave(&local_lock, flags);
     func3();
-    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags);
+    local_irq_restore(flags); -> local_unlock_irqrestore(&local_lock, flags);
   }
 
   func3()
diff --git a/Documentation/maintainer/maintainer-entry-profile.rst b/Documentation/maintainer/maintainer-entry-profile.rst
index 227f427..b7a627d 100644
--- a/Documentation/maintainer/maintainer-entry-profile.rst
+++ b/Documentation/maintainer/maintainer-entry-profile.rst
@@ -101,3 +101,4 @@
 
    ../doc-guide/maintainer-profile
    ../nvdimm/maintainer-entry-profile
+   ../riscv/patch-acceptance
diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst
index 24168b0..adc3146 100644
--- a/Documentation/networking/bonding.rst
+++ b/Documentation/networking/bonding.rst
@@ -2860,17 +2860,6 @@
 The latest version of this document can be found in the latest kernel
 source (named Documentation/networking/bonding.rst).
 
-Discussions regarding the usage of the bonding driver take place on the
-bonding-devel mailing list, hosted at sourceforge.net. If you have questions or
-problems, post them to the list.  The list address is:
-
-bonding-devel@lists.sourceforge.net
-
-The administrative interface (to subscribe or unsubscribe) can
-be found at:
-
-https://lists.sourceforge.net/lists/listinfo/bonding-devel
-
 Discussions regarding the development of the bonding driver take place
 on the main Linux network mailing list, hosted at vger.kernel.org. The list
 address is:
@@ -2881,10 +2870,3 @@
 be found at:
 
 http://vger.kernel.org/vger-lists.html#netdev
-
-Donald Becker's Ethernet Drivers and diag programs may be found at :
-
- - http://web.archive.org/web/%2E/http://www.scyld.com/network/
-
-You will also find a lot of information regarding Ethernet, NWay, MII,
-etc. at www.scyld.com.
diff --git a/Documentation/networking/dsa/configuration.rst b/Documentation/networking/dsa/configuration.rst
index af029b3c..11bd5e6 100644
--- a/Documentation/networking/dsa/configuration.rst
+++ b/Documentation/networking/dsa/configuration.rst
@@ -180,7 +180,7 @@
 
   # bring up the slave interfaces
   ip link set lan1 up
-  ip link set lan1 up
+  ip link set lan2 up
   ip link set lan3 up
 
   # create bridge
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index d53bcb3..b5a7988 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -206,6 +206,7 @@
   ``ETHTOOL_MSG_TSINFO_GET``		get timestamping info
   ``ETHTOOL_MSG_CABLE_TEST_ACT``        action start cable test
   ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT``    action start raw TDR cable test
+  ``ETHTOOL_MSG_TUNNEL_INFO_GET``       get tunnel offload info
   ===================================== ================================
 
 Kernel to userspace:
@@ -239,6 +240,7 @@
   ``ETHTOOL_MSG_TSINFO_GET_REPLY``	timestamping info
   ``ETHTOOL_MSG_CABLE_TEST_NTF``        Cable test results
   ``ETHTOOL_MSG_CABLE_TEST_TDR_NTF``    Cable test TDR results
+  ``ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY`` tunnel offload info
   ===================================== =================================
 
 ``GET`` requests are sent by userspace applications to retrieve device
@@ -1363,4 +1365,5 @@
   ``ETHTOOL_SFECPARAM``               n/a
   n/a                                 ''ETHTOOL_MSG_CABLE_TEST_ACT''
   n/a                                 ''ETHTOOL_MSG_CABLE_TEST_TDR_ACT''
+  n/a                                 ``ETHTOOL_MSG_TUNNEL_INFO_GET``
   =================================== =====================================
diff --git a/Documentation/powerpc/syscall64-abi.rst b/Documentation/powerpc/syscall64-abi.rst
index 46caaad..379817c 100644
--- a/Documentation/powerpc/syscall64-abi.rst
+++ b/Documentation/powerpc/syscall64-abi.rst
@@ -49,16 +49,18 @@
 Register preservation rules match the ELF ABI calling sequence with the
 following differences:
 
-=========== ============= ========================================
 --- For the sc instruction, differences with the ELF ABI ---
+=========== ============= ========================================
 r0          Volatile      (System call number.)
 r3          Volatile      (Parameter 1, and return value.)
 r4-r8       Volatile      (Parameters 2-6.)
 cr0         Volatile      (cr0.SO is the return error condition.)
 cr1, cr5-7  Nonvolatile
 lr          Nonvolatile
+=========== ============= ========================================
 
 --- For the scv 0 instruction, differences with the ELF ABI ---
+=========== ============= ========================================
 r0          Volatile      (System call number.)
 r3          Volatile      (Parameter 1, and return value.)
 r4-r8       Volatile      (Parameters 2-6.)
diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst
index 4a9aa4f..918e32d 100644
--- a/Documentation/process/deprecated.rst
+++ b/Documentation/process/deprecated.rst
@@ -142,7 +142,7 @@
 (Users of strscpy() still needing NUL-padding should instead
 use strscpy_pad().)
 
-If a caller is using non-NUL-terminated strings, strncpy()() can
+If a caller is using non-NUL-terminated strings, strncpy() can
 still be used, but destinations should be marked with the `__nonstring
 <https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html>`_
 attribute to avoid future compiler warnings.
diff --git a/Documentation/sound/cards/audigy-mixer.rst b/Documentation/sound/cards/audigy-mixer.rst
index 998f76e..f3f4640 100644
--- a/Documentation/sound/cards/audigy-mixer.rst
+++ b/Documentation/sound/cards/audigy-mixer.rst
@@ -332,7 +332,7 @@
 
 
 US Patents (https://www.uspto.gov/)
-----------------------------------
+-----------------------------------
 
 US 5925841
 	Digital Sampling Instrument employing cache memory (Jul. 20, 1999)
diff --git a/Documentation/sound/cards/sb-live-mixer.rst b/Documentation/sound/cards/sb-live-mixer.rst
index eccb0f0..2ce41d38 100644
--- a/Documentation/sound/cards/sb-live-mixer.rst
+++ b/Documentation/sound/cards/sb-live-mixer.rst
@@ -337,7 +337,7 @@
 
 
 US Patents (https://www.uspto.gov/)
-----------------------------------
+-----------------------------------
 
 US 5925841
 	Digital Sampling Instrument employing cache memory (Jul. 20, 1999)
diff --git a/Documentation/sound/designs/timestamping.rst b/Documentation/sound/designs/timestamping.rst
index 2b0fff5..7c7ecf5 100644
--- a/Documentation/sound/designs/timestamping.rst
+++ b/Documentation/sound/designs/timestamping.rst
@@ -143,7 +143,7 @@
 before returning from the ``STATUS`` and ``STATUS_EXT`` ioctl. in most cases
 this driver_timestamp will be identical to the regular system tstamp.
 
-Examples of typestamping with HDaudio:
+Examples of timestamping with HDAudio:
 
 1. DMA timestamp, no compensation for DMA+analog delay
 ::
diff --git a/Documentation/translations/it_IT/process/deprecated.rst b/Documentation/translations/it_IT/process/deprecated.rst
index e108eaf..a642ff3 100644
--- a/Documentation/translations/it_IT/process/deprecated.rst
+++ b/Documentation/translations/it_IT/process/deprecated.rst
@@ -130,7 +130,7 @@
 strscpy(). (chi usa strscpy() e necessita di estendere la
 terminazione con NUL deve aggiungere una chiamata a memset())
 
-Se il chiamate no usa stringhe terminate con NUL, allore strncpy()()
+Se il chiamate no usa stringhe terminate con NUL, allore strncpy()
 può continuare ad essere usata, ma i buffer di destinazione devono essere
 marchiati con l'attributo `__nonstring <https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html>`_
 per evitare avvisi durante la compilazione.
diff --git a/Documentation/userspace-api/media/v4l/buffer.rst b/Documentation/userspace-api/media/v4l/buffer.rst
index 57e752a..2044ed1 100644
--- a/Documentation/userspace-api/media/v4l/buffer.rst
+++ b/Documentation/userspace-api/media/v4l/buffer.rst
@@ -701,23 +701,6 @@
     :stub-columns: 0
     :widths:       3 1 4
 
-    * .. _`V4L2-FLAG-MEMORY-NON-CONSISTENT`:
-
-      - ``V4L2_FLAG_MEMORY_NON_CONSISTENT``
-      - 0x00000001
-      - A buffer is allocated either in consistent (it will be automatically
-	coherent between the CPU and the bus) or non-consistent memory. The
-	latter can provide performance gains, for instance the CPU cache
-	sync/flush operations can be avoided if the buffer is accessed by the
-	corresponding device only and the CPU does not read/write to/from that
-	buffer. However, this requires extra care from the driver -- it must
-	guarantee memory consistency by issuing a cache flush/sync when
-	consistency is needed. If this flag is set V4L2 will attempt to
-	allocate the buffer in non-consistent memory. The flag takes effect
-	only if the buffer is used for :ref:`memory mapping <mmap>` I/O and the
-	queue reports the :ref:`V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS
-	<V4L2-BUF-CAP-SUPPORTS-MMAP-CACHE-HINTS>` capability.
-
 .. c:type:: v4l2_memory
 
 enum v4l2_memory
diff --git a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst
index f2a70287..12cf6b4 100644
--- a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst
+++ b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst
@@ -120,13 +120,9 @@
 	If you want to just query the capabilities without making any
 	other changes, then set ``count`` to 0, ``memory`` to
 	``V4L2_MEMORY_MMAP`` and ``format.type`` to the buffer type.
-    * - __u32
-      - ``flags``
-      - Specifies additional buffer management attributes.
-	See :ref:`memory-flags`.
 
     * - __u32
-      - ``reserved``\ [6]
+      - ``reserved``\ [7]
       - A place holder for future extensions. Drivers and applications
 	must set the array to zero.
 
diff --git a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst
index 75d894d..0e3e2fd 100644
--- a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst
+++ b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst
@@ -112,17 +112,10 @@
 	``V4L2_MEMORY_MMAP`` and ``type`` set to the buffer type. This will
 	free any previously allocated buffers, so this is typically something
 	that will be done at the start of the application.
-    * - union {
-      - (anonymous)
-    * - __u32
-      - ``flags``
-      - Specifies additional buffer management attributes.
-	See :ref:`memory-flags`.
     * - __u32
       - ``reserved``\ [1]
-      - Kept for backwards compatibility. Use ``flags`` instead.
-    * - }
-      -
+      - A place holder for future extensions. Drivers and applications
+	must set the array to zero.
 
 .. tabularcolumns:: |p{6.1cm}|p{2.2cm}|p{8.7cm}|
 
@@ -169,7 +162,6 @@
       - This capability is set by the driver to indicate that the queue supports
         cache and memory management hints. However, it's only valid when the
         queue is used for :ref:`memory mapping <mmap>` streaming I/O. See
-        :ref:`V4L2_FLAG_MEMORY_NON_CONSISTENT <V4L2-FLAG-MEMORY-NON-CONSISTENT>`,
         :ref:`V4L2_BUF_FLAG_NO_CACHE_INVALIDATE <V4L2-BUF-FLAG-NO-CACHE-INVALIDATE>` and
         :ref:`V4L2_BUF_FLAG_NO_CACHE_CLEAN <V4L2-BUF-FLAG-NO-CACHE-CLEAN>`.
 
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index eb3a131..51191b5 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6130,7 +6130,7 @@
 8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
 -----------------------------------
 
-:Architecture: x86
+:Architectures: x86
 
 This capability indicates that KVM running on top of Hyper-V hypervisor
 enables Direct TLB flush for its guests meaning that TLB flush
@@ -6143,19 +6143,53 @@
 thinks it's running on Hyper-V and only use Hyper-V hypercalls.
 
 8.22 KVM_CAP_S390_VCPU_RESETS
+-----------------------------
 
-Architectures: s390
+:Architectures: s390
 
 This capability indicates that the KVM_S390_NORMAL_RESET and
 KVM_S390_CLEAR_RESET ioctls are available.
 
 8.23 KVM_CAP_S390_PROTECTED
+---------------------------
 
-Architecture: s390
-
+:Architectures: s390
 
 This capability indicates that the Ultravisor has been initialized and
 KVM can therefore start protected VMs.
 This capability governs the KVM_S390_PV_COMMAND ioctl and the
 KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected
 guests when the state change is invalid.
+
+8.24 KVM_CAP_STEAL_TIME
+-----------------------
+
+:Architectures: arm64, x86
+
+This capability indicates that KVM supports steal time accounting.
+When steal time accounting is supported it may be enabled with
+architecture-specific interfaces.  This capability and the architecture-
+specific interfaces must be consistent, i.e. if one says the feature
+is supported, than the other should as well and vice versa.  For arm64
+see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL".
+For x86 see Documentation/virt/kvm/msr.rst "MSR_KVM_STEAL_TIME".
+
+8.25 KVM_CAP_S390_DIAG318
+-------------------------
+
+:Architectures: s390
+
+This capability enables a guest to set information about its control program
+(i.e. guest kernel type and version). The information is helpful during
+system/firmware service events, providing additional data about the guest
+environments running on the machine.
+
+The information is associated with the DIAGNOSE 0x318 instruction, which sets
+an 8-byte value consisting of a one-byte Control Program Name Code (CPNC) and
+a 7-byte Control Program Version Code (CPVC). The CPNC determines what
+environment the control program is running in (e.g. Linux, z/VM...), and the
+CPVC is used for information specific to OS (e.g. Linux version, Linux
+distribution...)
+
+If this capability is available, then the CPNC and CPVC can be synchronized
+between KVM and userspace via the sync regs mechanism (KVM_SYNC_DIAG318).
diff --git a/Documentation/virt/kvm/arm/hyp-abi.rst b/Documentation/virt/kvm/arm/hyp-abi.rst
index d9eba93..83cadd8 100644
--- a/Documentation/virt/kvm/arm/hyp-abi.rst
+++ b/Documentation/virt/kvm/arm/hyp-abi.rst
@@ -54,9 +54,9 @@
     x3 = x1's value when entering the next payload (arm64)
     x4 = x2's value when entering the next payload (arm64)
 
-  Mask all exceptions, disable the MMU, move the arguments into place
-  (arm64 only), and jump to the restart address while at HYP/EL2. This
-  hypercall is not expected to return to its caller.
+  Mask all exceptions, disable the MMU, clear I+D bits, move the arguments
+  into place (arm64 only), and jump to the restart address while at HYP/EL2.
+  This hypercall is not expected to return to its caller.
 
 Any other value of r0/x0 triggers a hypervisor-specific handling,
 which is not documented here.
diff --git a/Documentation/x86/boot.rst b/Documentation/x86/boot.rst
index 7fafc7a..abb9fc1 100644
--- a/Documentation/x86/boot.rst
+++ b/Documentation/x86/boot.rst
@@ -1342,8 +1342,8 @@
 
 In addition to read/modify/write the setup header of the struct
 boot_params as that of 16-bit boot protocol, the boot loader should
-also fill the additional fields of the struct boot_params as that
-described in zero-page.txt.
+also fill the additional fields of the struct boot_params as
+described in chapter :doc:`zero-page`.
 
 After setting up the struct boot_params, the boot loader can load the
 32/64-bit kernel in the same way as that of 16-bit boot protocol.
@@ -1379,7 +1379,7 @@
 In addition to read/modify/write the setup header of the struct
 boot_params as that of 16-bit boot protocol, the boot loader should
 also fill the additional fields of the struct boot_params as described
-in zero-page.txt.
+in chapter :doc:`zero-page`.
 
 After setting up the struct boot_params, the boot loader can load
 64-bit kernel in the same way as that of 16-bit boot protocol, but
diff --git a/MAINTAINERS b/MAINTAINERS
index deaafb6..d61d45d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1460,6 +1460,11 @@
 F:	drivers/amba/
 F:	include/linux/amba/bus.h
 
+ARM PRIMECELL CLCD PL110 DRIVER
+M:	Russell King <linux@armlinux.org.uk>
+S:	Odd Fixes
+F:	drivers/video/fbdev/amba-clcd.*
+
 ARM PRIMECELL KMI PL050 DRIVER
 M:	Russell King <linux@armlinux.org.uk>
 S:	Odd Fixes
@@ -1623,7 +1628,7 @@
 
 ARM/Annapurna Labs ALPINE ARCHITECTURE
 M:	Tsahee Zidenberg <tsahee@annapurnalabs.com>
-M:	Antoine Tenart <antoine.tenart@bootlin.com>
+M:	Antoine Tenart <atenart@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/boot/dts/alpine*
@@ -1694,7 +1699,6 @@
 
 ARM/CAVIUM THUNDER NETWORK DRIVER
 M:	Sunil Goutham <sgoutham@marvell.com>
-M:	Robert Richter <rrichter@marvell.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/net/ethernet/cavium/thunder/
@@ -3205,6 +3209,7 @@
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 F:	block/
 F:	drivers/block/
+F:	include/linux/blk*
 F:	kernel/trace/blktrace.c
 F:	lib/sbitmap.c
 
@@ -3388,6 +3393,7 @@
 L:	netdev@vger.kernel.org
 L:	openwrt-devel@lists.openwrt.org (subscribers-only)
 S:	Supported
+F:	Documentation/devicetree/bindings/net/dsa/b53.txt
 F:	drivers/net/dsa/b53/*
 F:	include/linux/platform_data/b53.h
 
@@ -3573,13 +3579,28 @@
 S:	Maintained
 F:	drivers/phy/broadcom/phy-brcm-usb*
 
+BROADCOM ETHERNET PHY DRIVERS
+M:	Florian Fainelli <f.fainelli@gmail.com>
+L:	bcm-kernel-feedback-list@broadcom.com
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	Documentation/devicetree/bindings/net/broadcom-bcm87xx.txt
+F:	drivers/net/phy/bcm*.[ch]
+F:	drivers/net/phy/broadcom.c
+F:	include/linux/brcmphy.h
+
 BROADCOM GENET ETHERNET DRIVER
 M:	Doug Berger <opendmb@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	bcm-kernel-feedback-list@broadcom.com
 L:	netdev@vger.kernel.org
 S:	Supported
+F:	Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
+F:	Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt
 F:	drivers/net/ethernet/broadcom/genet/
+F:	drivers/net/mdio/mdio-bcm-unimac.c
+F:	include/linux/platform_data/bcmgenet.h
+F:	include/linux/platform_data/mdio-bcm-unimac.h
 
 BROADCOM IPROC ARM ARCHITECTURE
 M:	Ray Jui <rjui@broadcom.com>
@@ -3931,8 +3952,8 @@
 F:	drivers/net/wireless/ath/carl9170/
 
 CAVIUM I2C DRIVER
-M:	Robert Richter <rrichter@marvell.com>
-S:	Supported
+M:	Robert Richter <rric@kernel.org>
+S:	Odd Fixes
 W:	http://www.marvell.com
 F:	drivers/i2c/busses/i2c-octeon*
 F:	drivers/i2c/busses/i2c-thunderx*
@@ -3947,8 +3968,8 @@
 F:	drivers/net/ethernet/cavium/liquidio/
 
 CAVIUM MMC DRIVER
-M:	Robert Richter <rrichter@marvell.com>
-S:	Supported
+M:	Robert Richter <rric@kernel.org>
+S:	Odd Fixes
 W:	http://www.marvell.com
 F:	drivers/mmc/host/cavium*
 
@@ -3960,9 +3981,9 @@
 F:	drivers/crypto/cavium/cpt/
 
 CAVIUM THUNDERX2 ARM64 SOC
-M:	Robert Richter <rrichter@marvell.com>
+M:	Robert Richter <rric@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Maintained
+S:	Odd Fixes
 F:	Documentation/devicetree/bindings/arm/cavium-thunder2.txt
 F:	arch/arm64/boot/dts/cavium/thunder2-99xx*
 
@@ -4241,6 +4262,8 @@
 F:	.clang-format
 
 CLANG/LLVM BUILD SUPPORT
+M:	Nathan Chancellor <natechancellor@gmail.com>
+M:	Nick Desaulniers <ndesaulniers@google.com>
 L:	clang-built-linux@googlegroups.com
 S:	Supported
 W:	https://clangbuiltlinux.github.io/
@@ -4390,12 +4413,6 @@
 F:	fs/configfs/
 F:	include/linux/configfs.h
 
-CONNECTOR
-M:	Evgeniy Polyakov <zbr@ioremap.net>
-L:	netdev@vger.kernel.org
-S:	Maintained
-F:	drivers/connector/
-
 CONSOLE SUBSYSTEM
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 S:	Supported
@@ -5050,7 +5067,7 @@
 F:	include/uapi/linux/dm-*.h
 
 DEVLINK
-M:	Jiri Pirko <jiri@mellanox.com>
+M:	Jiri Pirko <jiri@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/devlink
@@ -5239,6 +5256,7 @@
 M:	Jonathan Corbet <corbet@lwn.net>
 L:	linux-doc@vger.kernel.org
 S:	Maintained
+P:	Documentation/doc-guide/maintainer-profile.rst
 T:	git git://git.lwn.net/linux.git docs-next
 F:	Documentation/
 F:	scripts/documentation-file-ref-check
@@ -6081,7 +6099,7 @@
 F:	lib/dynamic_debug.c
 
 DYNAMIC INTERRUPT MODERATION
-M:	Tal Gilboa <talgi@mellanox.com>
+M:	Tal Gilboa <talgi@nvidia.com>
 S:	Maintained
 F:	Documentation/networking/net_dim.rst
 F:	include/linux/dim.h
@@ -6161,7 +6179,7 @@
 F:	drivers/edac/aspeed_edac.c
 
 EDAC-BLUEFIELD
-M:	Shravan Kumar Ramani <sramani@mellanox.com>
+M:	Shravan Kumar Ramani <shravankr@nvidia.com>
 S:	Supported
 F:	drivers/edac/bluefield_edac.c
 
@@ -6173,16 +6191,15 @@
 
 EDAC-CAVIUM OCTEON
 M:	Ralf Baechle <ralf@linux-mips.org>
-M:	Robert Richter <rrichter@marvell.com>
 L:	linux-edac@vger.kernel.org
 L:	linux-mips@vger.kernel.org
 S:	Supported
 F:	drivers/edac/octeon_edac*
 
 EDAC-CAVIUM THUNDERX
-M:	Robert Richter <rrichter@marvell.com>
+M:	Robert Richter <rric@kernel.org>
 L:	linux-edac@vger.kernel.org
-S:	Supported
+S:	Odd Fixes
 F:	drivers/edac/thunderx_edac*
 
 EDAC-CORE
@@ -6190,7 +6207,7 @@
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 M:	Tony Luck <tony.luck@intel.com>
 R:	James Morse <james.morse@arm.com>
-R:	Robert Richter <rrichter@marvell.com>
+R:	Robert Richter <rric@kernel.org>
 L:	linux-edac@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras.git edac-for-next
@@ -6483,8 +6500,8 @@
 F:	drivers/net/ethernet/agere/
 
 ETHERNET BRIDGE
-M:	Roopa Prabhu <roopa@cumulusnetworks.com>
-M:	Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
+M:	Roopa Prabhu <roopa@nvidia.com>
+M:	Nikolay Aleksandrov <nikolay@nvidia.com>
 L:	bridge@lists.linux-foundation.org (moderated for non-subscribers)
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -6494,7 +6511,6 @@
 
 ETHERNET PHY LIBRARY
 M:	Andrew Lunn <andrew@lunn.ch>
-M:	Florian Fainelli <f.fainelli@gmail.com>
 M:	Heiner Kallweit <hkallweit1@gmail.com>
 R:	Russell King <linux@armlinux.org.uk>
 L:	netdev@vger.kernel.org
@@ -6599,7 +6615,7 @@
 
 EZchip NPS platform support
 M:	Vineet Gupta <vgupta@synopsys.com>
-M:	Ofer Levi <oferle@mellanox.com>
+M:	Ofer Levi <oferle@nvidia.com>
 S:	Supported
 F:	arch/arc/boot/dts/eznps.dts
 F:	arch/arc/plat-eznps
@@ -6884,6 +6900,14 @@
 S:	Maintained
 F:	drivers/dma/fsldma.*
 
+FREESCALE DSPI DRIVER
+M:	Vladimir Oltean <olteanv@gmail.com>
+L:	linux-spi@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt
+F:	drivers/spi/spi-fsl-dspi.c
+F:	include/linux/spi/spi-fsl-dspi.h
+
 FREESCALE ENETC ETHERNET DRIVERS
 M:	Claudiu Manoil <claudiu.manoil@nxp.com>
 L:	netdev@vger.kernel.org
@@ -7216,7 +7240,7 @@
 GCC PLUGINS
 M:	Kees Cook <keescook@chromium.org>
 R:	Emese Revfy <re.emese@gmail.com>
-L:	kernel-hardening@lists.openwall.com
+L:	linux-hardening@vger.kernel.org
 S:	Maintained
 F:	Documentation/kbuild/gcc-plugins.rst
 F:	scripts/Makefile.gcc-plugins
@@ -8255,7 +8279,7 @@
 M:	Tony Luck <tony.luck@intel.com>
 M:	Fenghua Yu <fenghua.yu@intel.com>
 L:	linux-ia64@vger.kernel.org
-S:	Maintained
+S:	Odd Fixes
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux.git
 F:	Documentation/ia64/
 F:	arch/ia64/
@@ -8304,8 +8328,9 @@
 F:	drivers/pci/hotplug/rpaphp*
 
 IBM Power SRIOV Virtual NIC Device Driver
-M:	Thomas Falcon <tlfalcon@linux.ibm.com>
-M:	John Allen <jallen@linux.ibm.com>
+M:	Dany Madden <drt@linux.ibm.com>
+M:	Lijun Pan <ljp@linux.ibm.com>
+M:	Sukadev Bhattiprolu <sukadev@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/ibm/ibmvnic.*
@@ -8319,7 +8344,7 @@
 F:	arch/powerpc/platforms/powernv/vas*
 
 IBM Power Virtual Ethernet Device Driver
-M:	Thomas Falcon <tlfalcon@linux.ibm.com>
+M:	Cristobal Forno <cforno12@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/ibm/ibmveth.*
@@ -8563,7 +8588,7 @@
 
 INFINIBAND SUBSYSTEM
 M:	Doug Ledford <dledford@redhat.com>
-M:	Jason Gunthorpe <jgg@mellanox.com>
+M:	Jason Gunthorpe <jgg@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	https://github.com/linux-rdma/rdma-core
@@ -8653,7 +8678,7 @@
 K:	\b(ABS|SYN)_MT_
 
 INSIDE SECURE CRYPTO DRIVER
-M:	Antoine Tenart <antoine.tenart@bootlin.com>
+M:	Antoine Tenart <atenart@kernel.org>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
 F:	drivers/crypto/inside-secure/
@@ -8732,7 +8757,8 @@
 F:	include/uapi/drm/i915_drm.h
 
 INTEL ETHERNET DRIVERS
-M:	Jeff Kirsher <jeffrey.t.kirsher@intel.com>
+M:	Jesse Brandeburg <jesse.brandeburg@intel.com>
+M:	Tony Nguyen <anthony.l.nguyen@intel.com>
 L:	intel-wired-lan@lists.osuosl.org (moderated for non-subscribers)
 S:	Supported
 W:	http://www.intel.com/support/feedback.htm
@@ -9226,7 +9252,7 @@
 
 ISCSI EXTENSIONS FOR RDMA (ISER) INITIATOR
 M:	Sagi Grimberg <sagi@grimberg.me>
-M:	Max Gurtovoy <maxg@mellanox.com>
+M:	Max Gurtovoy <mgurtovoy@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.openfabrics.org
@@ -9775,8 +9801,8 @@
 
 LEAKING_ADDRESSES
 M:	Tobin C. Harding <me@tobin.cc>
-M:	Tycho Andersen <tycho@tycho.ws>
-L:	kernel-hardening@lists.openwall.com
+M:	Tycho Andersen <tycho@tycho.pizza>
+L:	linux-hardening@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tobin/leaks.git
 F:	scripts/leaking_addresses.pl
@@ -11017,6 +11043,7 @@
 
 MEDIATEK SWITCH DRIVER
 M:	Sean Wang <sean.wang@mediatek.com>
+M:	Landen Chao <Landen.Chao@mediatek.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/dsa/mt7530.*
@@ -11072,7 +11099,7 @@
 F:	drivers/input/touchscreen/melfas_mip4.c
 
 MELLANOX ETHERNET DRIVER (mlx4_en)
-M:	Tariq Toukan <tariqt@mellanox.com>
+M:	Tariq Toukan <tariqt@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11080,7 +11107,7 @@
 F:	drivers/net/ethernet/mellanox/mlx4/en_*
 
 MELLANOX ETHERNET DRIVER (mlx5e)
-M:	Saeed Mahameed <saeedm@mellanox.com>
+M:	Saeed Mahameed <saeedm@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11088,7 +11115,7 @@
 F:	drivers/net/ethernet/mellanox/mlx5/core/en_*
 
 MELLANOX ETHERNET INNOVA DRIVERS
-R:	Boris Pismenny <borisp@mellanox.com>
+R:	Boris Pismenny <borisp@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11099,8 +11126,8 @@
 F:	include/linux/mlx5/mlx5_ifc_fpga.h
 
 MELLANOX ETHERNET SWITCH DRIVERS
-M:	Jiri Pirko <jiri@mellanox.com>
-M:	Ido Schimmel <idosch@mellanox.com>
+M:	Jiri Pirko <jiri@nvidia.com>
+M:	Ido Schimmel <idosch@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11109,7 +11136,7 @@
 F:	tools/testing/selftests/drivers/net/mlxsw/
 
 MELLANOX FIRMWARE FLASH LIBRARY (mlxfw)
-M:	mlxsw@mellanox.com
+M:	mlxsw@nvidia.com
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11119,7 +11146,7 @@
 MELLANOX HARDWARE PLATFORM SUPPORT
 M:	Andy Shevchenko <andy@infradead.org>
 M:	Darren Hart <dvhart@infradead.org>
-M:	Vadim Pasternak <vadimp@mellanox.com>
+M:	Vadim Pasternak <vadimp@nvidia.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Supported
 F:	Documentation/ABI/testing/sysfs-platform-mellanox-bootctl
@@ -11127,7 +11154,7 @@
 F:	include/linux/platform_data/mlxreg.h
 
 MELLANOX MLX4 core VPI driver
-M:	Tariq Toukan <tariqt@mellanox.com>
+M:	Tariq Toukan <tariqt@nvidia.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 S:	Supported
@@ -11137,7 +11164,7 @@
 F:	include/linux/mlx4/
 
 MELLANOX MLX4 IB driver
-M:	Yishai Hadas <yishaih@mellanox.com>
+M:	Yishai Hadas <yishaih@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11147,8 +11174,8 @@
 F:	include/uapi/rdma/mlx4-abi.h
 
 MELLANOX MLX5 core VPI driver
-M:	Saeed Mahameed <saeedm@mellanox.com>
-M:	Leon Romanovsky <leonro@mellanox.com>
+M:	Saeed Mahameed <saeedm@nvidia.com>
+M:	Leon Romanovsky <leonro@nvidia.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 S:	Supported
@@ -11159,7 +11186,7 @@
 F:	include/linux/mlx5/
 
 MELLANOX MLX5 IB driver
-M:	Leon Romanovsky <leonro@mellanox.com>
+M:	Leon Romanovsky <leonro@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -11169,8 +11196,8 @@
 F:	include/uapi/rdma/mlx5-abi.h
 
 MELLANOX MLXCPLD I2C AND MUX DRIVER
-M:	Vadim Pasternak <vadimp@mellanox.com>
-M:	Michael Shych <michaelsh@mellanox.com>
+M:	Vadim Pasternak <vadimp@nvidia.com>
+M:	Michael Shych <michaelsh@nvidia.com>
 L:	linux-i2c@vger.kernel.org
 S:	Supported
 F:	Documentation/i2c/busses/i2c-mlxcpld.rst
@@ -11178,7 +11205,7 @@
 F:	drivers/i2c/muxes/i2c-mux-mlxcpld.c
 
 MELLANOX MLXCPLD LED DRIVER
-M:	Vadim Pasternak <vadimp@mellanox.com>
+M:	Vadim Pasternak <vadimp@nvidia.com>
 L:	linux-leds@vger.kernel.org
 S:	Supported
 F:	Documentation/leds/leds-mlxcpld.rst
@@ -11186,7 +11213,7 @@
 F:	drivers/leds/leds-mlxreg.c
 
 MELLANOX PLATFORM DRIVER
-M:	Vadim Pasternak <vadimp@mellanox.com>
+M:	Vadim Pasternak <vadimp@nvidia.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Supported
 F:	drivers/platform/x86/mlx-platform.c
@@ -12030,6 +12057,7 @@
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
 F:	Documentation/devicetree/bindings/net/
+F:	drivers/connector/
 F:	drivers/net/
 F:	include/linux/etherdevice.h
 F:	include/linux/fcdevice.h
@@ -12055,6 +12083,7 @@
 M:	Andrew Lunn <andrew@lunn.ch>
 M:	Vivien Didelot <vivien.didelot@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
+M:	Vladimir Oltean <olteanv@gmail.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/dsa/
 F:	drivers/net/dsa/
@@ -12167,8 +12196,8 @@
 F:	net/ipv6/tcp*.c
 
 NETWORKING [TLS]
-M:	Boris Pismenny <borisp@mellanox.com>
-M:	Aviad Yehezkel <aviadye@mellanox.com>
+M:	Boris Pismenny <borisp@nvidia.com>
+M:	Aviad Yehezkel <aviadye@nvidia.com>
 M:	John Fastabend <john.fastabend@gmail.com>
 M:	Daniel Borkmann <daniel@iogearbox.net>
 M:	Jakub Kicinski <kuba@kernel.org>
@@ -12468,7 +12497,7 @@
 F:	drivers/nfc/nxp-nci
 
 OBJAGG
-M:	Jiri Pirko <jiri@mellanox.com>
+M:	Jiri Pirko <jiri@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	include/linux/objagg.h
@@ -13110,7 +13139,7 @@
 F:	include/linux/hp_sdc.h
 
 PARMAN
-M:	Jiri Pirko <jiri@mellanox.com>
+M:	Jiri Pirko <jiri@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	include/linux/parman.h
@@ -13160,6 +13189,7 @@
 
 PCI DRIVER FOR AARDVARK (Marvell Armada 3700)
 M:	Thomas Petazzoni <thomas.petazzoni@bootlin.com>
+M:	Pali Rohár <pali@kernel.org>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -13429,10 +13459,10 @@
 F:	drivers/pci/controller/dwc/*artpec*
 
 PCIE DRIVER FOR CAVIUM THUNDERX
-M:	Robert Richter <rrichter@marvell.com>
+M:	Robert Richter <rric@kernel.org>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
+S:	Odd Fixes
 F:	drivers/pci/controller/pci-thunder-*
 
 PCIE DRIVER FOR HISILICON
@@ -13569,12 +13599,18 @@
 F:	tools/lib/perf/
 F:	tools/perf/
 
-PERFORMANCE EVENTS SUBSYSTEM ARM64 PMU EVENTS
+PERFORMANCE EVENTS TOOLING ARM64
 R:	John Garry <john.garry@huawei.com>
 R:	Will Deacon <will@kernel.org>
+R:	Mathieu Poirier <mathieu.poirier@linaro.org>
+R:	Leo Yan <leo.yan@linaro.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
+F:	tools/build/feature/test-libopencsd.c
+F:	tools/perf/arch/arm*/
 F:	tools/perf/pmu-events/arch/arm64/
+F:	tools/perf/util/arm-spe*
+F:	tools/perf/util/cs-etm*
 
 PERSONALITY HANDLING
 M:	Christoph Hellwig <hch@infradead.org>
@@ -14365,7 +14401,7 @@
 L:	iommu@lists.linux-foundation.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
-F:	drivers/iommu/qcom_iommu.c
+F:	drivers/iommu/arm/arm-smmu/qcom_iommu.c
 
 QUALCOMM IPCC MAILBOX DRIVER
 M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
@@ -15546,6 +15582,7 @@
 SECURITY CONTACT
 M:	Security Officers <security@kernel.org>
 S:	Supported
+F:	Documentation/admin-guide/security-bugs.rst
 
 SECURITY SUBSYSTEM
 M:	James Morris <jmorris@namei.org>
@@ -16034,7 +16071,7 @@
 F:	include/uapi/rdma/siw-abi.h
 
 SOFT-ROCE DRIVER (rxe)
-M:	Zhu Yanjun <yanjunz@mellanox.com>
+M:	Zhu Yanjun <yanjunz@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/sw/rxe/
@@ -16125,7 +16162,7 @@
 L:	linux-media@vger.kernel.org
 S:	Maintained
 T:	git git://linuxtv.org/media_tree.git
-F:	Documentation/devicetree/bindings/media/i2c/imx274.txt
+F:	Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
 F:	drivers/media/i2c/imx274.c
 
 SONY IMX290 SENSOR DRIVER
@@ -16695,6 +16732,13 @@
 F:	Documentation/devicetree/bindings/gpio/snps,dw-apb-gpio.yaml
 F:	drivers/gpio/gpio-dwapb.c
 
+SYNOPSYS DESIGNWARE APB SSI DRIVER
+M:	Serge Semin <fancer.lancer@gmail.com>
+L:	linux-spi@vger.kernel.org
+S:	Supported
+F:	Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
+F:	drivers/spi/spi-dw*
+
 SYNOPSYS DESIGNWARE AXI DMAC DRIVER
 M:	Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
 S:	Maintained
@@ -17116,8 +17160,8 @@
 F:	Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml
 F:	Documentation/devicetree/bindings/arm/keystone/ti,sci.txt
 F:	Documentation/devicetree/bindings/clock/ti,sci-clk.txt
-F:	Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt
-F:	Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.txt
+F:	Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
+F:	Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml
 F:	Documentation/devicetree/bindings/reset/ti,sci-reset.txt
 F:	Documentation/devicetree/bindings/soc/ti/sci-pm-domain.txt
 F:	drivers/clk/keystone/sci-clk.c
@@ -17214,8 +17258,8 @@
 F:	drivers/net/thunderbolt.c
 
 THUNDERX GPIO DRIVER
-M:	Robert Richter <rrichter@marvell.com>
-S:	Maintained
+M:	Robert Richter <rric@kernel.org>
+S:	Odd Fixes
 F:	drivers/gpio/gpio-thunderx.c
 
 TI AM437X VPFE DRIVER
@@ -17561,7 +17605,7 @@
 S:	Maintained
 W:	https://kernsec.org/wiki/index.php/Linux_Kernel_Integrity
 Q:	https://patchwork.kernel.org/project/linux-integrity/list/
-T:	git git://git.infradead.org/users/jjs/linux-tpmdd.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd.git
 F:	drivers/char/tpm/
 
 TRACING
@@ -18252,7 +18296,8 @@
 F:	include/linux/vga_switcheroo.h
 
 VIA RHINE NETWORK DRIVER
-S:	Orphan
+S:	Maintained
+M:	Kevin Brace <kevinbrace@bracecomputerlab.com>
 F:	drivers/net/ethernet/via/via-rhine.c
 
 VIA SD/MMC CARD CONTROLLER DRIVER
@@ -18857,10 +18902,10 @@
 F:	arch/x86/mm/
 
 X86 PLATFORM DRIVERS
-M:	Darren Hart <dvhart@infradead.org>
-M:	Andy Shevchenko <andy@infradead.org>
+M:	Hans de Goede <hdegoede@redhat.com>
+M:	Mark Gross <mgross@linux.intel.com>
 L:	platform-driver-x86@vger.kernel.org
-S:	Odd Fixes
+S:	Maintained
 T:	git git://git.infradead.org/linux-platform-drivers-x86.git
 F:	drivers/platform/olpc/
 F:	drivers/platform/x86/
@@ -18874,6 +18919,15 @@
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
 F:	arch/x86/platform
 
+X86 PLATFORM UV HPE SUPERDOME FLEX
+M:	Steve Wahl <steve.wahl@hpe.com>
+R:	Dimitri Sivanich <dimitri.sivanich@hpe.com>
+R:	Russ Anderson <russ.anderson@hpe.com>
+S:	Supported
+F:	arch/x86/include/asm/uv/
+F:	arch/x86/kernel/apic/x2apic_uv_x.c
+F:	arch/x86/platform/uv/
+
 X86 VDSO
 M:	Andy Lutomirski <luto@kernel.org>
 L:	linux-kernel@vger.kernel.org
diff --git a/Makefile b/Makefile
index 9cac6fd..51540b2 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
@@ -265,8 +265,7 @@
 			 $(version_h) headers headers_% archheaders archscripts \
 			 %asm-generic kernelversion %src-pkg dt_binding_check \
 			 outputmakefile
-no-sync-config-targets := $(no-dot-config-targets) install %install \
-			   kernelrelease
+no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease
 single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/
 
 config-build	:=
@@ -292,7 +291,7 @@
 endif
 
 ifeq ($(KBUILD_EXTMOD),)
-        ifneq ($(filter config %config,$(MAKECMDGOALS)),)
+        ifneq ($(filter %config,$(MAKECMDGOALS)),)
 		config-build := 1
                 ifneq ($(words $(MAKECMDGOALS)),1)
 			mixed-build := 1
@@ -883,10 +882,6 @@
 LDFLAGS_vmlinux += --gc-sections
 endif
 
-ifdef CONFIG_LIVEPATCH
-KBUILD_CFLAGS += $(call cc-option, -flive-patching=inline-clone)
-endif
-
 ifdef CONFIG_SHADOW_CALL_STACK
 CC_FLAGS_SCS	:= -fsanitize=shadow-call-stack
 KBUILD_CFLAGS	+= $(CC_FLAGS_SCS)
diff --git a/arch/alpha/kernel/module.c b/arch/alpha/kernel/module.c
index ac110ae..5b60c24 100644
--- a/arch/alpha/kernel/module.c
+++ b/arch/alpha/kernel/module.c
@@ -212,7 +212,7 @@
 			    STO_ALPHA_STD_GPLOAD)
 				/* Omit the prologue. */
 				value += 8;
-			/* FALLTHRU */
+			fallthrough;
 		case R_ALPHA_BRADDR:
 			value -= (u64)location + 4;
 			if (value & 3)
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index a813020..15bc9d1 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -453,7 +453,7 @@
 			regs->r0 = EINTR;
 			break;
 		}
-		/* fallthrough */
+		fallthrough;
 	case ERESTARTNOINTR:
 		regs->r0 = r0;	/* reset v0 and a3 and replay syscall */
 		regs->r19 = r19;
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index 49754e0..921d4b6 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -883,7 +883,7 @@
 
 	case 0x26: /* sts */
 		fake_reg = s_reg_to_mem(alpha_read_fp_reg(reg));
-		/* FALLTHRU */
+		fallthrough;
 
 	case 0x2c: /* stl */
 		__asm__ __volatile__(
@@ -911,7 +911,7 @@
 
 	case 0x27: /* stt */
 		fake_reg = alpha_read_fp_reg(reg);
-		/* FALLTHRU */
+		fallthrough;
 
 	case 0x2d: /* stq */
 		__asm__ __volatile__(
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 9acbeba..dcaa44e 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -88,6 +88,8 @@
 
 	arcpct: pct {
 		compatible = "snps,archs-pct";
+		interrupt-parent = <&cpu_intc>;
+		interrupts = <20>;
 	};
 
 	/* TIMER0 with interrupt for clockevent */
@@ -208,7 +210,7 @@
 			reg = <0x8000 0x2000>;
 			interrupts = <10>;
 			interrupt-names = "macirq";
-			phy-mode = "rgmii";
+			phy-mode = "rgmii-id";
 			snps,pbl = <32>;
 			snps,multicast-filter-bins = <256>;
 			clocks = <&gmacclk>;
@@ -226,7 +228,7 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				compatible = "snps,dwmac-mdio";
-				phy0: ethernet-phy@0 {
+				phy0: ethernet-phy@0 { /* Micrel KSZ9031 */
 					reg = <0>;
 				};
 			};
diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h
index b747f2e..6147db9 100644
--- a/arch/arc/include/asm/pgalloc.h
+++ b/arch/arc/include/asm/pgalloc.h
@@ -18,10 +18,10 @@
  * vineetg: April 2010
  *  -Switched pgtable_t from being struct page * to unsigned long
  *      =Needed so that Page Table allocator (pte_alloc_one) is not forced to
- *       to deal with struct page. Thay way in future we can make it allocate
+ *       deal with struct page. That way in future we can make it allocate
  *       multiple PG Tbls in one Page Frame
  *      =sweet side effect is avoiding calls to ugly page_address( ) from the
- *       pg-tlb allocator sub-sys (pte_alloc_one, ptr_free, pmd_populate
+ *       pg-tlb allocator sub-sys (pte_alloc_one, ptr_free, pmd_populate)
  *
  *  Amit Bhor, Sameer Dhavale: Codito Technologies 2004
  */
diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c
index d04837d..03f8b1b 100644
--- a/arch/arc/kernel/disasm.c
+++ b/arch/arc/kernel/disasm.c
@@ -339,7 +339,7 @@
 
 	case op_LDWX_S:	/* LDWX_S c, [b, u6] */
 		state->x = 1;
-		/* intentional fall-through */
+		fallthrough;
 
 	case op_LDW_S:	/* LDW_S c, [b, u6] */
 		state->zz = 2;
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 661fd84..79849f3 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -562,7 +562,7 @@
 {
 	struct arc_reg_pct_build pct_bcr;
 	struct arc_reg_cc_build cc_bcr;
-	int i, has_interrupts;
+	int i, has_interrupts, irq;
 	int counter_size;	/* in bits */
 
 	union cc_name {
@@ -637,13 +637,7 @@
 		.attr_groups	= arc_pmu->attr_groups,
 	};
 
-	if (has_interrupts) {
-		int irq = platform_get_irq(pdev, 0);
-
-		if (irq < 0) {
-			pr_err("Cannot get IRQ number for the platform\n");
-			return -ENODEV;
-		}
+	if (has_interrupts && (irq = platform_get_irq(pdev, 0) >= 0)) {
 
 		arc_pmu->irq = irq;
 
@@ -652,9 +646,9 @@
 				   this_cpu_ptr(&arc_pmu_cpu));
 
 		on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);
-
-	} else
+	} else {
 		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+	}
 
 	/*
 	 * perf parser doesn't really like '-' symbol in events name, so let's
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 3d57ed0..8222f8c 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -321,7 +321,7 @@
 			regs->r0 = -EINTR;
 			break;
 		}
-		/* fallthrough */
+		fallthrough;
 
 	case -ERESTARTNOINTR:
 		/*
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 28e8bf0..a331bb5 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -18,44 +18,37 @@
 
 #define ARC_PATH_MAX	256
 
-/*
- * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
- *   -Prints 3 regs per line and a CR.
- *   -To continue, callee regs right after scratch, special handling of CR
- */
-static noinline void print_reg_file(long *reg_rev, int start_num)
+static noinline void print_regs_scratch(struct pt_regs *regs)
 {
-	unsigned int i;
-	char buf[512];
-	int n = 0, len = sizeof(buf);
+	pr_cont("BTA: 0x%08lx\n SP: 0x%08lx  FP: 0x%08lx BLK: %pS\n",
+		regs->bta, regs->sp, regs->fp, (void *)regs->blink);
+	pr_cont("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
+		regs->lp_start, regs->lp_end, regs->lp_count);
 
-	for (i = start_num; i < start_num + 13; i++) {
-		n += scnprintf(buf + n, len - n, "r%02u: 0x%08lx\t",
-			       i, (unsigned long)*reg_rev);
-
-		if (((i + 1) % 3) == 0)
-			n += scnprintf(buf + n, len - n, "\n");
-
-		/* because pt_regs has regs reversed: r12..r0, r25..r13 */
-		if (is_isa_arcv2() && start_num == 0)
-			reg_rev++;
-		else
-			reg_rev--;
-	}
-
-	if (start_num != 0)
-		n += scnprintf(buf + n, len - n, "\n\n");
-
-	/* To continue printing callee regs on same line as scratch regs */
-	if (start_num == 0)
-		pr_info("%s", buf);
-	else
-		pr_cont("%s\n", buf);
+	pr_info("r00: 0x%08lx\tr01: 0x%08lx\tr02: 0x%08lx\n"	\
+		"r03: 0x%08lx\tr04: 0x%08lx\tr05: 0x%08lx\n"	\
+		"r06: 0x%08lx\tr07: 0x%08lx\tr08: 0x%08lx\n"	\
+		"r09: 0x%08lx\tr10: 0x%08lx\tr11: 0x%08lx\n"	\
+		"r12: 0x%08lx\t",
+		regs->r0, regs->r1, regs->r2,
+		regs->r3, regs->r4, regs->r5,
+		regs->r6, regs->r7, regs->r8,
+		regs->r9, regs->r10, regs->r11,
+		regs->r12);
 }
 
-static void show_callee_regs(struct callee_regs *cregs)
+static void print_regs_callee(struct callee_regs *regs)
 {
-	print_reg_file(&(cregs->r13), 13);
+	pr_cont("r13: 0x%08lx\tr14: 0x%08lx\n"			\
+		"r15: 0x%08lx\tr16: 0x%08lx\tr17: 0x%08lx\n"	\
+		"r18: 0x%08lx\tr19: 0x%08lx\tr20: 0x%08lx\n"	\
+		"r21: 0x%08lx\tr22: 0x%08lx\tr23: 0x%08lx\n"	\
+		"r24: 0x%08lx\tr25: 0x%08lx\n",
+		regs->r13, regs->r14,
+		regs->r15, regs->r16, regs->r17,
+		regs->r18, regs->r19, regs->r20,
+		regs->r21, regs->r22, regs->r23,
+		regs->r24, regs->r25);
 }
 
 static void print_task_path_n_nm(struct task_struct *tsk)
@@ -175,7 +168,7 @@
 void show_regs(struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
-	struct callee_regs *cregs;
+	struct callee_regs *cregs = (struct callee_regs *)tsk->thread.callee_reg;
 
 	/*
 	 * generic code calls us with preemption disabled, but some calls
@@ -204,25 +197,15 @@
 			STS_BIT(regs, A2), STS_BIT(regs, A1),
 			STS_BIT(regs, E2), STS_BIT(regs, E1));
 #else
-	pr_cont(" [%2s%2s%2s%2s]",
+	pr_cont(" [%2s%2s%2s%2s]   ",
 			STS_BIT(regs, IE),
 			(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
 			STS_BIT(regs, DE), STS_BIT(regs, AE));
 #endif
-	pr_cont("  BTA: 0x%08lx\n  SP: 0x%08lx  FP: 0x%08lx BLK: %pS\n",
-		regs->bta, regs->sp, regs->fp, (void *)regs->blink);
-	pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
-		regs->lp_start, regs->lp_end, regs->lp_count);
 
-	/* print regs->r0 thru regs->r12
-	 * Sequential printing was generating horrible code
-	 */
-	print_reg_file(&(regs->r0), 0);
-
-	/* If Callee regs were saved, display them too */
-	cregs = (struct callee_regs *)current->thread.callee_reg;
+	print_regs_scratch(regs);
 	if (cregs)
-		show_callee_regs(cregs);
+		print_regs_callee(cregs);
 
 	preempt_disable();
 }
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index f87758a..74ad425 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -572,7 +572,7 @@
 #else
 		BUILD_BUG_ON(sizeof(u32) != sizeof(value));
 #endif
-		/* Fall through */
+		fallthrough;
 	case DW_EH_PE_native:
 		if (end < (const void *)(ptr.pul + 1))
 			return 0;
@@ -827,7 +827,7 @@
 			case DW_CFA_def_cfa:
 				state->cfa.reg = get_uleb128(&ptr.p8, end);
 				unw_debug("cfa_def_cfa: r%lu ", state->cfa.reg);
-				/* fall through */
+				fallthrough;
 			case DW_CFA_def_cfa_offset:
 				state->cfa.offs = get_uleb128(&ptr.p8, end);
 				unw_debug("cfa_def_cfa_offset: 0x%lx ",
@@ -835,7 +835,7 @@
 				break;
 			case DW_CFA_def_cfa_sf:
 				state->cfa.reg = get_uleb128(&ptr.p8, end);
-				/* fall through */
+				fallthrough;
 			case DW_CFA_def_cfa_offset_sf:
 				state->cfa.offs = get_sleb128(&ptr.p8, end)
 				    * state->dataAlign;
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index f886ac6..3a35b82 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -26,8 +26,8 @@
 
 #ifdef CONFIG_HIGHMEM
 static unsigned long min_high_pfn, max_high_pfn;
-static u64 high_mem_start;
-static u64 high_mem_sz;
+static phys_addr_t high_mem_start;
+static phys_addr_t high_mem_sz;
 #endif
 
 #ifdef CONFIG_DISCONTIGMEM
@@ -69,6 +69,7 @@
 		high_mem_sz = size;
 		in_use = 1;
 		memblock_add_node(base, size, 1);
+		memblock_reserve(base, size);
 #endif
 	}
 
@@ -157,7 +158,7 @@
 	min_high_pfn = PFN_DOWN(high_mem_start);
 	max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz);
 
-	max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn;
+	max_zone_pfn[ZONE_HIGHMEM] = min_low_pfn;
 
 	high_memory = (void *)(min_high_pfn << PAGE_SHIFT);
 	kmap_init();
@@ -166,6 +167,17 @@
 	free_area_init(max_zone_pfn);
 }
 
+static void __init highmem_init(void)
+{
+#ifdef CONFIG_HIGHMEM
+	unsigned long tmp;
+
+	memblock_free(high_mem_start, high_mem_sz);
+	for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++)
+		free_highmem_page(pfn_to_page(tmp));
+#endif
+}
+
 /*
  * mem_init - initializes memory
  *
@@ -174,14 +186,7 @@
  */
 void __init mem_init(void)
 {
-#ifdef CONFIG_HIGHMEM
-	unsigned long tmp;
-
-	reset_all_zones_managed_pages();
-	for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++)
-		free_highmem_page(pfn_to_page(tmp));
-#endif
-
 	memblock_free_all();
+	highmem_init();
 	mem_init_print_info(NULL);
 }
diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h
index a4a6153..77712c5 100644
--- a/arch/arc/plat-eznps/include/plat/ctop.h
+++ b/arch/arc/plat-eznps/include/plat/ctop.h
@@ -33,7 +33,6 @@
 #define CTOP_AUX_DPC				(CTOP_AUX_BASE + 0x02C)
 #define CTOP_AUX_LPC				(CTOP_AUX_BASE + 0x030)
 #define CTOP_AUX_EFLAGS				(CTOP_AUX_BASE + 0x080)
-#define CTOP_AUX_IACK				(CTOP_AUX_BASE + 0x088)
 #define CTOP_AUX_GPA1				(CTOP_AUX_BASE + 0x08C)
 #define CTOP_AUX_UDMC				(CTOP_AUX_BASE + 0x300)
 
diff --git a/arch/arm/boot/dts/at91-sama5d2_icp.dts b/arch/arm/boot/dts/at91-sama5d2_icp.dts
index 8d19925..6783cf1 100644
--- a/arch/arm/boot/dts/at91-sama5d2_icp.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_icp.dts
@@ -116,7 +116,6 @@
 		switch0: ksz8563@0 {
 			compatible = "microchip,ksz8563";
 			reg = <0>;
-			phy-mode = "mii";
 			reset-gpios = <&pioA PIN_PD4 GPIO_ACTIVE_LOW>;
 
 			spi-max-frequency = <500000>;
@@ -140,6 +139,7 @@
 					reg = <2>;
 					label = "cpu";
 					ethernet = <&macb0>;
+					phy-mode = "mii";
 					fixed-link {
 						speed = <100>;
 						full-duplex;
diff --git a/arch/arm/boot/dts/bcm-hr2.dtsi b/arch/arm/boot/dts/bcm-hr2.dtsi
index cbebed5..e8df458 100644
--- a/arch/arm/boot/dts/bcm-hr2.dtsi
+++ b/arch/arm/boot/dts/bcm-hr2.dtsi
@@ -217,7 +217,7 @@
 		};
 
 		qspi: spi@27200 {
-			compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+			compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 			reg = <0x027200 0x184>,
 			      <0x027000 0x124>,
 			      <0x11c408 0x004>,
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index 0346ea6..c846fa3 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -284,7 +284,7 @@
 		};
 
 		qspi: spi@27200 {
-			compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+			compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 			reg = <0x027200 0x184>,
 			      <0x027000 0x124>,
 			      <0x11c408 0x004>,
diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi
index f7ae5a4..d94357b 100644
--- a/arch/arm/boot/dts/bcm2835-rpi.dtsi
+++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi
@@ -13,7 +13,7 @@
 
 	soc {
 		firmware: firmware {
-			compatible = "raspberrypi,bcm2835-firmware", "simple-bus";
+			compatible = "raspberrypi,bcm2835-firmware", "simple-mfd";
 			#address-cells = <1>;
 			#size-cells = <1>;
 
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 2d9b4dd..0016720 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -488,7 +488,7 @@
 	};
 
 	spi@18029200 {
-		compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+		compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 		reg = <0x18029200 0x184>,
 		      <0x18029000 0x124>,
 		      <0x1811b408 0x004>,
diff --git a/arch/arm/boot/dts/imx6q-logicpd.dts b/arch/arm/boot/dts/imx6q-logicpd.dts
index 7a3d1d3..8f94364 100644
--- a/arch/arm/boot/dts/imx6q-logicpd.dts
+++ b/arch/arm/boot/dts/imx6q-logicpd.dts
@@ -13,7 +13,7 @@
 
 	backlight: backlight-lvds {
 		compatible = "pwm-backlight";
-		pwms = <&pwm3 0 20000>;
+		pwms = <&pwm3 0 20000 0>;
 		brightness-levels = <0 4 8 16 32 64 128 255>;
 		default-brightness-level = <6>;
 		power-supply = <&reg_lcd>;
diff --git a/arch/arm/boot/dts/imx6q-prtwd2.dts b/arch/arm/boot/dts/imx6q-prtwd2.dts
index dffafbc..349959d 100644
--- a/arch/arm/boot/dts/imx6q-prtwd2.dts
+++ b/arch/arm/boot/dts/imx6q-prtwd2.dts
@@ -30,7 +30,7 @@
 	};
 
 	/* PRTWD2 rev 1 bitbang I2C for Ethernet Switch */
-	i2c@4 {
+	i2c {
 		compatible = "i2c-gpio";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_i2c4>;
diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
index 7705285..4d01c33 100644
--- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
@@ -22,8 +22,6 @@
 
 	gpio-keys {
 		compatible = "gpio-keys";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
 		user-pb {
 			label = "user_pb";
diff --git a/arch/arm/boot/dts/imx6sx-pinfunc.h b/arch/arm/boot/dts/imx6sx-pinfunc.h
index 0b02c7e..f4dc462 100644
--- a/arch/arm/boot/dts/imx6sx-pinfunc.h
+++ b/arch/arm/boot/dts/imx6sx-pinfunc.h
@@ -1026,7 +1026,7 @@
 #define MX6SX_PAD_QSPI1B_DQS__SIM_M_HADDR_15                      0x01B0 0x04F8 0x0000 0x7 0x0
 #define MX6SX_PAD_QSPI1B_SCLK__QSPI1_B_SCLK                       0x01B4 0x04FC 0x0000 0x0 0x0
 #define MX6SX_PAD_QSPI1B_SCLK__UART3_DCE_RX                       0x01B4 0x04FC 0x0840 0x1 0x4
-#define MX6SX_PAD_QSPI1B_SCLK__UART3_DTE_TX                       0x01B4 0x04FC 0x0000 0x0 0x0
+#define MX6SX_PAD_QSPI1B_SCLK__UART3_DTE_TX                       0x01B4 0x04FC 0x0000 0x1 0x0
 #define MX6SX_PAD_QSPI1B_SCLK__ECSPI3_SCLK                        0x01B4 0x04FC 0x0730 0x2 0x1
 #define MX6SX_PAD_QSPI1B_SCLK__ESAI_RX_HF_CLK                     0x01B4 0x04FC 0x0780 0x3 0x2
 #define MX6SX_PAD_QSPI1B_SCLK__CSI1_DATA_16                       0x01B4 0x04FC 0x06DC 0x4 0x1
diff --git a/arch/arm/boot/dts/imx7d-zii-rmu2.dts b/arch/arm/boot/dts/imx7d-zii-rmu2.dts
index e5e20b0..7cb6153 100644
--- a/arch/arm/boot/dts/imx7d-zii-rmu2.dts
+++ b/arch/arm/boot/dts/imx7d-zii-rmu2.dts
@@ -58,7 +58,7 @@
 			  <&clks IMX7D_ENET1_TIME_ROOT_CLK>;
 	assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>;
 	assigned-clock-rates = <0>, <100000000>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&fec1_phy>;
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/imx7ulp.dtsi b/arch/arm/boot/dts/imx7ulp.dtsi
index 3674396..b7ea37a 100644
--- a/arch/arm/boot/dts/imx7ulp.dtsi
+++ b/arch/arm/boot/dts/imx7ulp.dtsi
@@ -394,7 +394,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLC>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 0 32>;
+			gpio-ranges = <&iomuxc1 0 0 20>;
 		};
 
 		gpio_ptd: gpio@40af0000 {
@@ -408,7 +408,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLD>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 32 32>;
+			gpio-ranges = <&iomuxc1 0 32 12>;
 		};
 
 		gpio_pte: gpio@40b00000 {
@@ -422,7 +422,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLE>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 64 32>;
+			gpio-ranges = <&iomuxc1 0 64 16>;
 		};
 
 		gpio_ptf: gpio@40b10000 {
@@ -436,7 +436,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLF>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 96 32>;
+			gpio-ranges = <&iomuxc1 0 96 20>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi
index 100396f..395e05f 100644
--- a/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi
@@ -51,6 +51,8 @@
 
 &mcbsp2 {
 	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcbsp2_pins>;
 };
 
 &charger {
@@ -102,35 +104,18 @@
 		regulator-max-microvolt = <3300000>;
 	};
 
-	lcd0: display@0 {
-		compatible = "panel-dpi";
-		label = "28";
-		status = "okay";
-		/* default-on; */
+	lcd0: display {
+		/* This isn't the exact LCD, but the timings meet spec */
+		compatible = "logicpd,type28";
 		pinctrl-names = "default";
 		pinctrl-0 = <&lcd_enable_pin>;
-		enable-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>;	/* gpio155, lcd INI */
+		backlight = <&bl>;
+		enable-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>;
 		port {
 			lcd_in: endpoint {
 				remote-endpoint = <&dpi_out>;
 			};
 		};
-
-		panel-timing {
-			clock-frequency = <9000000>;
-			hactive = <480>;
-			vactive = <272>;
-			hfront-porch = <3>;
-			hback-porch = <2>;
-			hsync-len = <42>;
-			vback-porch = <3>;
-			vfront-porch = <2>;
-			vsync-len = <11>;
-			hsync-active = <1>;
-			vsync-active = <1>;
-			de-active = <1>;
-			pixelclk-active = <0>;
-		};
 	};
 
 	bl: backlight {
diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
index 381f0e8..b0f6613 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
@@ -81,6 +81,8 @@
 };
 
 &mcbsp2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcbsp2_pins>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi
index 069af9a..827373e 100644
--- a/arch/arm/boot/dts/ls1021a.dtsi
+++ b/arch/arm/boot/dts/ls1021a.dtsi
@@ -182,7 +182,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0x0 0x1550000 0x0 0x10000>,
-			      <0x0 0x40000000 0x0 0x40000000>;
+			      <0x0 0x40000000 0x0 0x20000000>;
 			reg-names = "QuadSPI", "QuadSPI-memory";
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
 			clock-names = "qspi_en", "qspi";
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 5da9cff..a82c962 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -488,11 +488,11 @@
 					};
 				};
 
-				target-module@5000 {
+				target-module@4000 {
 					compatible = "ti,sysc-omap2", "ti,sysc";
-					reg = <0x5000 0x4>,
-					      <0x5010 0x4>,
-					      <0x5014 0x4>;
+					reg = <0x4000 0x4>,
+					      <0x4010 0x4>,
+					      <0x4014 0x4>;
 					reg-names = "rev", "sysc", "syss";
 					ti,sysc-sidle = <SYSC_IDLE_FORCE>,
 							<SYSC_IDLE_NO>,
@@ -504,7 +504,7 @@
 					ti,syss-mask = <1>;
 					#address-cells = <1>;
 					#size-cells = <1>;
-					ranges = <0 0x5000 0x1000>;
+					ranges = <0 0x4000 0x1000>;
 
 					dsi1: encoder@0 {
 						compatible = "ti,omap5-dsi";
@@ -514,8 +514,9 @@
 						reg-names = "proto", "phy", "pll";
 						interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
 						status = "disabled";
-						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>;
-						clock-names = "fck";
+						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>,
+							 <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 10>;
+						clock-names = "fck", "sys_clk";
 					};
 				};
 
@@ -545,8 +546,9 @@
 						reg-names = "proto", "phy", "pll";
 						interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
 						status = "disabled";
-						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>;
-						clock-names = "fck";
+						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>,
+							 <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 10>;
+						clock-names = "fck", "sys_clk";
 					};
 				};
 
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index fc4abef..0013ec3 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -821,7 +821,7 @@
 		timer3: timer3@ffd00100 {
 			compatible = "snps,dw-apb-timer";
 			interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>;
-			reg = <0xffd01000 0x100>;
+			reg = <0xffd00100 0x100>;
 			clocks = <&l4_sys_free_clk>;
 			clock-names = "timer";
 			resets = <&rst L4SYSTIMER1_RESET>;
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index 0fe03aa..2259d11 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -495,7 +495,7 @@
 			};
 
 			ocotp: ocotp@400a5000 {
-				compatible = "fsl,vf610-ocotp";
+				compatible = "fsl,vf610-ocotp", "syscon";
 				reg = <0x400a5000 0x1000>;
 				clocks = <&clks VF610_CLK_OCOTP>;
 			};
diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig
index a9755c5..b06e537 100644
--- a/arch/arm/configs/integrator_defconfig
+++ b/arch/arm/configs/integrator_defconfig
@@ -1,13 +1,11 @@
 CONFIG_SYSVIPC=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_PREEMPT=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PARTITION_ADVANCED=y
 CONFIG_ARCH_MULTI_V4T=y
 CONFIG_ARCH_MULTI_V5=y
 # CONFIG_ARCH_MULTI_V7 is not set
@@ -15,19 +13,17 @@
 CONFIG_ARCH_INTEGRATOR_AP=y
 CONFIG_INTEGRATOR_IMPD1=y
 CONFIG_ARCH_INTEGRATOR_CP=y
-CONFIG_PCI=y
-CONFIG_PREEMPT=y
 CONFIG_AEABI=y
 # CONFIG_ATAGS is not set
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="console=ttyAM0,38400n8 root=/dev/nfs ip=bootp"
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_CPUFREQ_DT=y
-CONFIG_CMA=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -37,6 +33,7 @@
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 # CONFIG_IPV6 is not set
+CONFIG_PCI=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_AFS_PARTS=y
@@ -52,9 +49,12 @@
 CONFIG_NETDEVICES=y
 CONFIG_E100=y
 CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
 # CONFIG_KEYBOARD_ATKBD is not set
+CONFIG_KEYBOARD_GPIO=y
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_DRM=y
+CONFIG_DRM_DISPLAY_CONNECTOR=y
 CONFIG_DRM_SIMPLE_BRIDGE=y
 CONFIG_DRM_PL111=y
 CONFIG_FB_MODE_HELPERS=y
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 7fff88e..7a4853b 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -547,7 +547,7 @@
 		if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE)
 			&& max_watchpoint_len >= 8)
 			break;
-		/* Else, fall through */
+		fallthrough;
 	default:
 		return -EINVAL;
 	}
@@ -612,12 +612,12 @@
 		/* Allow halfword watchpoints and breakpoints. */
 		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 			break;
-		/* Else, fall through */
+		fallthrough;
 	case 3:
 		/* Allow single byte watchpoint. */
 		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 			break;
-		/* Else, fall through */
+		fallthrough;
 	default:
 		ret = -EINVAL;
 		goto out;
@@ -884,7 +884,7 @@
 		break;
 	case ARM_ENTRY_ASYNC_WATCHPOINT:
 		WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n");
-		/* Fall through */
+		fallthrough;
 	case ARM_ENTRY_SYNC_WATCHPOINT:
 		watchpoint_handler(addr, fsr, regs);
 		break;
@@ -933,7 +933,7 @@
 		ARM_DBG_READ(c1, c1, 4, oslsr);
 		if (oslsr & ARM_OSLSR_OSLM0)
 			return true;
-		/* Else, fall through */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index c9dc912..c1892f7 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -596,7 +596,7 @@
 		switch (retval) {
 		case -ERESTART_RESTARTBLOCK:
 			restart -= 2;
-			/* Fall through */
+			fallthrough;
 		case -ERESTARTNOHAND:
 		case -ERESTARTSYS:
 		case -ERESTARTNOINTR:
diff --git a/arch/arm/mach-ep93xx/crunch.c b/arch/arm/mach-ep93xx/crunch.c
index 1c05c5b..757032d 100644
--- a/arch/arm/mach-ep93xx/crunch.c
+++ b/arch/arm/mach-ep93xx/crunch.c
@@ -49,7 +49,7 @@
 		 * FALLTHROUGH: Ensure we don't try to overwrite our newly
 		 * initialised state information on the first fault.
 		 */
-		/* Fall through */
+		fallthrough;
 
 	case THREAD_NOTIFY_EXIT:
 		crunch_task_release(thread);
diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c
index 24dd5bb..094337d 100644
--- a/arch/arm/mach-imx/cpuidle-imx6q.c
+++ b/arch/arm/mach-imx/cpuidle-imx6q.c
@@ -24,7 +24,9 @@
 		imx6_set_lpm(WAIT_UNCLOCKED);
 	raw_spin_unlock(&cpuidle_lock);
 
+	rcu_idle_enter();
 	cpu_do_idle();
+	rcu_idle_exit();
 
 	raw_spin_lock(&cpuidle_lock);
 	if (num_idle_cpus-- == num_online_cpus())
@@ -44,7 +46,7 @@
 		{
 			.exit_latency = 50,
 			.target_residency = 75,
-			.flags = CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIMER_STOP | CPUIDLE_FLAG_RCU_IDLE,
 			.enter = imx6q_enter_wait,
 			.name = "WAIT",
 			.desc = "Clock off",
diff --git a/arch/arm/mach-mmp/pm-mmp2.c b/arch/arm/mach-mmp/pm-mmp2.c
index 2d86381..7a6f74c 100644
--- a/arch/arm/mach-mmp/pm-mmp2.c
+++ b/arch/arm/mach-mmp/pm-mmp2.c
@@ -123,19 +123,19 @@
 	case POWER_MODE_SYS_SLEEP:
 		apcr |= MPMU_PCR_PJ_SLPEN;		/* set the SLPEN bit */
 		apcr |= MPMU_PCR_PJ_VCTCXOSD;		/* set VCTCXOSD */
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_CHIP_SLEEP:
 		apcr |= MPMU_PCR_PJ_SLPEN;
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_APPS_SLEEP:
 		apcr |= MPMU_PCR_PJ_APBSD;		/* set APBSD */
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_APPS_IDLE:
 		apcr |= MPMU_PCR_PJ_AXISD;		/* set AXISDD bit */
 		apcr |= MPMU_PCR_PJ_DDRCORSD;		/* set DDRCORSD bit */
 		idle_cfg |= APMU_PJ_IDLE_CFG_PJ_PWRDWN;	/* PJ power down */
 		apcr |= MPMU_PCR_PJ_SPSD;
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_CORE_EXTIDLE:
 		idle_cfg |= APMU_PJ_IDLE_CFG_PJ_IDLE;	/* set the IDLE bit */
 		idle_cfg &= ~APMU_PJ_IDLE_CFG_ISO_MODE_CNTRL_MASK;
diff --git a/arch/arm/mach-mmp/pm-pxa910.c b/arch/arm/mach-mmp/pm-pxa910.c
index 69ebe18..1d71d73 100644
--- a/arch/arm/mach-mmp/pm-pxa910.c
+++ b/arch/arm/mach-mmp/pm-pxa910.c
@@ -145,23 +145,23 @@
 	case POWER_MODE_UDR:
 		/* only shutdown APB in UDR */
 		apcr |= MPMU_APCR_STBYEN | MPMU_APCR_APBSD;
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_SYS_SLEEP:
 		apcr |= MPMU_APCR_SLPEN;		/* set the SLPEN bit */
 		apcr |= MPMU_APCR_VCTCXOSD;		/* set VCTCXOSD */
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_APPS_SLEEP:
 		apcr |= MPMU_APCR_DDRCORSD;		/* set DDRCORSD */
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_APPS_IDLE:
 		apcr |= MPMU_APCR_AXISD;		/* set AXISDD bit */
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_CORE_EXTIDLE:
 		idle_cfg |= APMU_MOH_IDLE_CFG_MOH_IDLE;
 		idle_cfg |= APMU_MOH_IDLE_CFG_MOH_PWRDWN;
 		idle_cfg |= APMU_MOH_IDLE_CFG_MOH_PWR_SW(3)
 			| APMU_MOH_IDLE_CFG_MOH_L2_PWR_SW(3);
-		/* fall through */
+		fallthrough;
 	case POWER_MODE_CORE_INTIDLE:
 		break;
 	}
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index 1d119b9..59755b5 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -396,7 +396,6 @@
 			cpu_rev = "3.1";
 			break;
 		case 7:
-		/* FALLTHROUGH */
 		default:
 			/* Use the latest known revision as default */
 			omap_revision = OMAP3430_REV_ES3_1_2;
@@ -416,7 +415,6 @@
 			cpu_rev = "1.0";
 			break;
 		case 1:
-		/* FALLTHROUGH */
 		default:
 			omap_revision = AM35XX_REV_ES1_1;
 			cpu_rev = "1.1";
@@ -435,7 +433,6 @@
 			cpu_rev = "1.1";
 			break;
 		case 2:
-		/* FALLTHROUGH */
 		default:
 			omap_revision = OMAP3630_REV_ES1_2;
 			cpu_rev = "1.2";
@@ -456,7 +453,6 @@
 			cpu_rev = "2.0";
 			break;
 		case 3:
-			/* FALLTHROUGH */
 		default:
 			omap_revision = TI8168_REV_ES2_1;
 			cpu_rev = "2.1";
@@ -473,7 +469,6 @@
 			cpu_rev = "2.0";
 			break;
 		case 2:
-		/* FALLTHROUGH */
 		default:
 			omap_revision = AM335X_REV_ES2_1;
 			cpu_rev = "2.1";
@@ -491,7 +486,6 @@
 			cpu_rev = "1.1";
 			break;
 		case 2:
-		/* FALLTHROUGH */
 		default:
 			omap_revision = AM437X_REV_ES1_2;
 			cpu_rev = "1.2";
@@ -502,7 +496,6 @@
 	case 0xb968:
 		switch (rev) {
 		case 0:
-		/* FALLTHROUGH */
 		case 1:
 			omap_revision = TI8148_REV_ES1_0;
 			cpu_rev = "1.0";
@@ -512,7 +505,6 @@
 			cpu_rev = "2.0";
 			break;
 		case 3:
-		/* FALLTHROUGH */
 		default:
 			omap_revision = TI8148_REV_ES2_1;
 			cpu_rev = "2.1";
diff --git a/arch/arm/mach-omap2/omap-iommu.c b/arch/arm/mach-omap2/omap-iommu.c
index 54aff33..bfa5e1b 100644
--- a/arch/arm/mach-omap2/omap-iommu.c
+++ b/arch/arm/mach-omap2/omap-iommu.c
@@ -74,7 +74,7 @@
 		return pwrdm;
 
 	clk = of_clk_get(dev->of_node->parent, 0);
-	if (!clk) {
+	if (IS_ERR(clk)) {
 		dev_err(dev, "no fck found\n");
 		return NULL;
 	}
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 6b4548f..fc7bb2c 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -240,7 +240,7 @@
 		if (pdev->dev.of_node)
 			omap_device_build_from_dt(pdev);
 		omap_auxdata_legacy_init(dev);
-		/* fall through */
+		fallthrough;
 	default:
 		od = to_omap_device(pdev);
 		if (od)
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 6df395f..f5dfddf 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -298,11 +298,7 @@
 	if (omap_irq_pending())
 		return;
 
-	trace_cpu_idle_rcuidle(1, smp_processor_id());
-
 	omap_sram_idle();
-
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 #ifdef CONFIG_SUSPEND
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index d13344b..87cb472 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -624,7 +624,7 @@
 		 dns323ab_leds[0].active_low = 1;
 		 gpio_request(DNS323_GPIO_LED_POWER1, "Power Led Enable");
 		 gpio_direction_output(DNS323_GPIO_LED_POWER1, 0);
-		/* Fall through */
+		fallthrough;
 	case DNS323_REV_B1:
 		i2c_register_board_info(0, dns323ab_i2c_devices,
 				ARRAY_SIZE(dns323ab_i2c_devices));
diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c
index ea2c842..d23970b 100644
--- a/arch/arm/mach-rpc/riscpc.c
+++ b/arch/arm/mach-rpc/riscpc.c
@@ -46,7 +46,7 @@
 	switch (tag->u.acorn.vram_pages) {
 	case 512:
 		vram_size += PAGE_SIZE * 256;
-		/* Fall through - ??? */
+		fallthrough;	/* ??? */
 	case 256:
 		vram_size += PAGE_SIZE * 256;
 	default:
diff --git a/arch/arm/mach-tegra/reset.c b/arch/arm/mach-tegra/reset.c
index 76a65df..d5c805a 100644
--- a/arch/arm/mach-tegra/reset.c
+++ b/arch/arm/mach-tegra/reset.c
@@ -70,7 +70,7 @@
 	switch (err) {
 	case -ENOSYS:
 		tegra_cpu_reset_handler_set(reset_address);
-		/* fall through */
+		fallthrough;
 	case 0:
 		is_enabled = true;
 		break;
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index f4bfc1c..ea81e89 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -694,7 +694,7 @@
 			return subset[(L<<1) | ((tinstr & (1<<8)) >> 8)] |
 			    (tinstr & 255);		/* register_list */
 		}
-		/* Else, fall through - for illegal instruction case */
+		fallthrough;	/* for illegal instruction case */
 
 	default:
 		return BAD_INSTR;
@@ -750,7 +750,7 @@
 	case 0xe8e0:
 	case 0xe9e0:
 		poffset->un = (tinst2 & 0xff) << 2;
-		/* Fall through */
+		fallthrough;
 
 	case 0xe940:
 	case 0xe9c0:
diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c
index c0fbfca5d..114c05a 100644
--- a/arch/arm/mm/proc-v7-bugs.c
+++ b/arch/arm/mm/proc-v7-bugs.c
@@ -71,7 +71,7 @@
 		/* Other ARM CPUs require no workaround */
 		if (read_cpuid_implementor() == ARM_CPU_IMP_ARM)
 			break;
-		/* fallthrough */
+		fallthrough;
 		/* Cortex A57/A72 require firmware workaround */
 	case ARM_CPU_PART_CORTEX_A57:
 	case ARM_CPU_PART_CORTEX_A72: {
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index b2e9e82..1eb5900 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -309,14 +309,14 @@
 		 * not supported by current hardware on OMAP1
 		 * w |= (0x03 << 7);
 		 */
-		/* fall through */
+		fallthrough;
 	case OMAP_DMA_DATA_BURST_16:
 		if (dma_omap2plus()) {
 			burst = 0x3;
 			break;
 		}
 		/* OMAP1 don't support burst 16 */
-		/* fall through */
+		fallthrough;
 	default:
 		BUG();
 	}
@@ -393,7 +393,7 @@
 			break;
 		}
 		/* OMAP1 don't support burst 16 */
-		/* fall through */
+		fallthrough;
 	default:
 		printk(KERN_ERR "Invalid DMA burst mode\n");
 		BUG();
diff --git a/arch/arm/probes/decode.c b/arch/arm/probes/decode.c
index fe81a9c..c84053a 100644
--- a/arch/arm/probes/decode.c
+++ b/arch/arm/probes/decode.c
@@ -307,7 +307,7 @@
 		case REG_TYPE_NOPCWB:
 			if (!is_writeback(insn))
 				break; /* No writeback, so any register is OK */
-			/* fall through... */
+			fallthrough;
 		case REG_TYPE_NOPC:
 		case REG_TYPE_NOPCX:
 			/* Reject PC (R15) */
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index 90b5bc7..feefa20 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -280,7 +280,7 @@
 				/* A nested probe was hit in FIQ, it is a BUG */
 				pr_warn("Unrecoverable kprobe detected.\n");
 				dump_kprobe(p);
-				/* fall through */
+				fallthrough;
 			default:
 				/* impossible cases */
 				BUG();
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index e93145d..a6ab368 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -150,7 +150,7 @@
 	pr_info("Xen: initializing cpu%d\n", cpu);
 	vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
 
-	info.mfn = virt_to_gfn(vcpup);
+	info.mfn = percpu_to_gfn(vcpup);
 	info.offset = xen_offset_in_page(vcpup);
 
 	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 6d23283..43091f4 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -29,6 +29,7 @@
 	select ARCH_HAS_SETUP_DMA_OPS
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_SET_MEMORY
+	select ARCH_STACKWALK
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
@@ -211,12 +212,18 @@
 	default 14 if ARM64_16K_PAGES
 	default 12
 
-config ARM64_CONT_SHIFT
+config ARM64_CONT_PTE_SHIFT
 	int
 	default 5 if ARM64_64K_PAGES
 	default 7 if ARM64_16K_PAGES
 	default 4
 
+config ARM64_CONT_PMD_SHIFT
+	int
+	default 5 if ARM64_64K_PAGES
+	default 5 if ARM64_16K_PAGES
+	default 4
+
 config ARCH_MMAP_RND_BITS_MIN
        default 14 if ARM64_64K_PAGES
        default 16 if ARM64_16K_PAGES
@@ -1165,32 +1172,6 @@
 
 	  If unsure, say Y.
 
-config HARDEN_BRANCH_PREDICTOR
-	bool "Harden the branch predictor against aliasing attacks" if EXPERT
-	default y
-	help
-	  Speculation attacks against some high-performance processors rely on
-	  being able to manipulate the branch predictor for a victim context by
-	  executing aliasing branches in the attacker context.  Such attacks
-	  can be partially mitigated against by clearing internal branch
-	  predictor state and limiting the prediction logic in some situations.
-
-	  This config option will take CPU-specific actions to harden the
-	  branch predictor against aliasing attacks and may rely on specific
-	  instruction sequences or control bits being set by the system
-	  firmware.
-
-	  If unsure, say Y.
-
-config ARM64_SSBD
-	bool "Speculative Store Bypass Disable" if EXPERT
-	default y
-	help
-	  This enables mitigation of the bypassing of previous stores
-	  by speculative loads.
-
-	  If unsure, say Y.
-
 config RODATA_FULL_DEFAULT_ENABLED
 	bool "Apply r/o permissions of VM areas also to their linear aliases"
 	default y
@@ -1664,6 +1645,39 @@
 	  provides a high bandwidth, cryptographically secure
 	  hardware random number generator.
 
+config ARM64_AS_HAS_MTE
+	# Initial support for MTE went in binutils 2.32.0, checked with
+	# ".arch armv8.5-a+memtag" below. However, this was incomplete
+	# as a late addition to the final architecture spec (LDGM/STGM)
+	# is only supported in the newer 2.32.x and 2.33 binutils
+	# versions, hence the extra "stgm" instruction check below.
+	def_bool $(as-instr,.arch armv8.5-a+memtag\nstgm xzr$(comma)[x0])
+
+config ARM64_MTE
+	bool "Memory Tagging Extension support"
+	default y
+	depends on ARM64_AS_HAS_MTE && ARM64_TAGGED_ADDR_ABI
+	select ARCH_USES_HIGH_VMA_FLAGS
+	help
+	  Memory Tagging (part of the ARMv8.5 Extensions) provides
+	  architectural support for run-time, always-on detection of
+	  various classes of memory error to aid with software debugging
+	  to eliminate vulnerabilities arising from memory-unsafe
+	  languages.
+
+	  This option enables the support for the Memory Tagging
+	  Extension at EL0 (i.e. for userspace).
+
+	  Selecting this option allows the feature to be detected at
+	  runtime. Any secondary CPU not implementing this feature will
+	  not be allowed a late bring-up.
+
+	  Userspace binaries that want to use this feature must
+	  explicitly opt in. The mechanism for the userspace is
+	  described in:
+
+	  Documentation/arm64/memory-tagging-extension.rst.
+
 endmenu
 
 config ARM64_SVE
@@ -1876,6 +1890,10 @@
 	def_bool y
 	depends on HUGETLB_PAGE && MIGRATION
 
+config ARCH_ENABLE_THP_MIGRATION
+	def_bool y
+	depends on TRANSPARENT_HUGEPAGE
+
 menu "Power management options"
 
 source "kernel/power/Kconfig"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 55bc854..0fd4c1b 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -11,7 +11,6 @@
 # Copyright (C) 1995-2001 by Russell King
 
 LDFLAGS_vmlinux	:=--no-undefined -X
-CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
 
 ifeq ($(CONFIG_RELOCATABLE), y)
 # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour
@@ -82,8 +81,8 @@
 # compiler to generate them and consequently to break the single image contract
 # we pass it only to the assembler. This option is utilized only in case of non
 # integrated assemblers.
-ifneq ($(CONFIG_AS_HAS_ARMV8_4), y)
-branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a
+ifeq ($(CONFIG_AS_HAS_PAC), y)
+asm-arch := armv8.3-a
 endif
 endif
 
@@ -91,7 +90,12 @@
 
 ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
 # make sure to pass the newest target architecture to -march.
-KBUILD_CFLAGS	+= -Wa,-march=armv8.4-a
+asm-arch := armv8.4-a
+endif
+
+ifdef asm-arch
+KBUILD_CFLAGS	+= -Wa,-march=$(asm-arch) \
+		   -DARM64_ASM_ARCH='"$(asm-arch)"'
 endif
 
 ifeq ($(CONFIG_SHADOW_CALL_STACK), y)
@@ -127,9 +131,6 @@
 # Default value
 head-y		:= arch/arm64/kernel/head.o
 
-# The byte offset of the kernel image in RAM from the start of RAM.
-TEXT_OFFSET := 0x0
-
 ifeq ($(CONFIG_KASAN_SW_TAGS), y)
 KASAN_SHADOW_SCALE_SHIFT := 4
 else
@@ -140,8 +141,6 @@
 KBUILD_CPPFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
 KBUILD_AFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
 
-export	TEXT_OFFSET
-
 core-y		+= arch/arm64/
 libs-y		:= arch/arm64/lib/ $(libs-y)
 libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
@@ -165,6 +164,8 @@
 PHONY += vdso_install
 vdso_install:
 	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@
+	$(if $(CONFIG_COMPAT_VDSO), \
+		$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@)
 
 # We use MRPROPER_FILES and CLEAN_FILES now
 archclean:
diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
index 15f7b0e..3980206 100644
--- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
@@ -745,7 +745,7 @@
 		};
 
 		qspi: spi@66470200 {
-			compatible = "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi";
+			compatible = "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi";
 			reg = <0x66470200 0x184>,
 				<0x66470000 0x124>,
 				<0x67017408 0x004>,
diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile
index a39f0a1..903c0eb 100644
--- a/arch/arm64/boot/dts/freescale/Makefile
+++ b/arch/arm64/boot/dts/freescale/Makefile
@@ -28,6 +28,7 @@
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-qds.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-rdb.dtb
 
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-beacon-kit.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-ddr4-evk.dtb
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index 9de2aa1..a5154f1 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -702,7 +702,7 @@
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MP_CLK_SDMA1_ROOT>,
-					 <&clk IMX8MP_CLK_SDMA1_ROOT>;
+					 <&clk IMX8MP_CLK_AHB>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx7d.bin";
diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
index f70435c..561fa79 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
@@ -423,7 +423,7 @@
 			tmu: tmu@30260000 {
 				compatible = "fsl,imx8mq-tmu";
 				reg = <0x30260000 0x10000>;
-				interrupt = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MQ_CLK_TMU_ROOT>;
 				little-endian;
 				fsl,tmu-range = <0xb0000 0xa0026 0x80048 0x70061>;
diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
index 1a39e0e..5b9ec03 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
@@ -686,6 +686,8 @@
 		clocks = <&pericfg CLK_PERI_MSDC30_0_PD>,
 			 <&topckgen CLK_TOP_MSDC50_0_SEL>;
 		clock-names = "source", "hclk";
+		resets = <&pericfg MT7622_PERI_MSDC0_SW_RST>;
+		reset-names = "hrst";
 		status = "disabled";
 	};
 
diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
index 34d249d..8eb61dd 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
@@ -337,8 +337,9 @@
 		compatible = "nvidia,tegra186-sdhci";
 		reg = <0x0 0x03400000 0x0 0x10000>;
 		interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&bpmp TEGRA186_CLK_SDMMC1>;
-		clock-names = "sdhci";
+		clocks = <&bpmp TEGRA186_CLK_SDMMC1>,
+			 <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&bpmp TEGRA186_RESET_SDMMC1>;
 		reset-names = "sdhci";
 		interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRA &emc>,
@@ -366,8 +367,9 @@
 		compatible = "nvidia,tegra186-sdhci";
 		reg = <0x0 0x03420000 0x0 0x10000>;
 		interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&bpmp TEGRA186_CLK_SDMMC2>;
-		clock-names = "sdhci";
+		clocks = <&bpmp TEGRA186_CLK_SDMMC2>,
+			 <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&bpmp TEGRA186_RESET_SDMMC2>;
 		reset-names = "sdhci";
 		interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRAA &emc>,
@@ -390,8 +392,9 @@
 		compatible = "nvidia,tegra186-sdhci";
 		reg = <0x0 0x03440000 0x0 0x10000>;
 		interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&bpmp TEGRA186_CLK_SDMMC3>;
-		clock-names = "sdhci";
+		clocks = <&bpmp TEGRA186_CLK_SDMMC3>,
+			 <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&bpmp TEGRA186_RESET_SDMMC3>;
 		reset-names = "sdhci";
 		interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCR &emc>,
@@ -416,8 +419,9 @@
 		compatible = "nvidia,tegra186-sdhci";
 		reg = <0x0 0x03460000 0x0 0x10000>;
 		interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&bpmp TEGRA186_CLK_SDMMC4>;
-		clock-names = "sdhci";
+		clocks = <&bpmp TEGRA186_CLK_SDMMC4>,
+			 <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>;
+		clock-names = "sdhci", "tmclk";
 		assigned-clocks = <&bpmp TEGRA186_CLK_SDMMC4>,
 				  <&bpmp TEGRA186_CLK_PLLC4_VCO>;
 		assigned-clock-parents = <&bpmp TEGRA186_CLK_PLLC4_VCO>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index 48160f4..ca5cb6a 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -460,8 +460,9 @@
 			compatible = "nvidia,tegra194-sdhci";
 			reg = <0x03400000 0x10000>;
 			interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bpmp TEGRA194_CLK_SDMMC1>;
-			clock-names = "sdhci";
+			clocks = <&bpmp TEGRA194_CLK_SDMMC1>,
+				 <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>;
+			clock-names = "sdhci", "tmclk";
 			resets = <&bpmp TEGRA194_RESET_SDMMC1>;
 			reset-names = "sdhci";
 			interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCRA &emc>,
@@ -485,8 +486,9 @@
 			compatible = "nvidia,tegra194-sdhci";
 			reg = <0x03440000 0x10000>;
 			interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bpmp TEGRA194_CLK_SDMMC3>;
-			clock-names = "sdhci";
+			clocks = <&bpmp TEGRA194_CLK_SDMMC3>,
+				 <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>;
+			clock-names = "sdhci", "tmclk";
 			resets = <&bpmp TEGRA194_RESET_SDMMC3>;
 			reset-names = "sdhci";
 			interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCR &emc>,
@@ -511,8 +513,9 @@
 			compatible = "nvidia,tegra194-sdhci";
 			reg = <0x03460000 0x10000>;
 			interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bpmp TEGRA194_CLK_SDMMC4>;
-			clock-names = "sdhci";
+			clocks = <&bpmp TEGRA194_CLK_SDMMC4>,
+				 <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>;
+			clock-names = "sdhci", "tmclk";
 			assigned-clocks = <&bpmp TEGRA194_CLK_SDMMC4>,
 					  <&bpmp TEGRA194_CLK_PLLC4>;
 			assigned-clock-parents =
diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
index 829f786..8cca216 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
@@ -1194,8 +1194,9 @@
 		compatible = "nvidia,tegra210-sdhci";
 		reg = <0x0 0x700b0000 0x0 0x200>;
 		interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&tegra_car TEGRA210_CLK_SDMMC1>;
-		clock-names = "sdhci";
+		clocks = <&tegra_car TEGRA210_CLK_SDMMC1>,
+			 <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&tegra_car 14>;
 		reset-names = "sdhci";
 		pinctrl-names = "sdmmc-3v3", "sdmmc-1v8",
@@ -1222,8 +1223,9 @@
 		compatible = "nvidia,tegra210-sdhci";
 		reg = <0x0 0x700b0200 0x0 0x200>;
 		interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&tegra_car TEGRA210_CLK_SDMMC2>;
-		clock-names = "sdhci";
+		clocks = <&tegra_car TEGRA210_CLK_SDMMC2>,
+			 <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&tegra_car 9>;
 		reset-names = "sdhci";
 		pinctrl-names = "sdmmc-1v8-drv";
@@ -1239,8 +1241,9 @@
 		compatible = "nvidia,tegra210-sdhci";
 		reg = <0x0 0x700b0400 0x0 0x200>;
 		interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&tegra_car TEGRA210_CLK_SDMMC3>;
-		clock-names = "sdhci";
+		clocks = <&tegra_car TEGRA210_CLK_SDMMC3>,
+			 <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&tegra_car 69>;
 		reset-names = "sdhci";
 		pinctrl-names = "sdmmc-3v3", "sdmmc-1v8",
@@ -1262,8 +1265,9 @@
 		compatible = "nvidia,tegra210-sdhci";
 		reg = <0x0 0x700b0600 0x0 0x200>;
 		interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&tegra_car TEGRA210_CLK_SDMMC4>;
-		clock-names = "sdhci";
+		clocks = <&tegra_car TEGRA210_CLK_SDMMC4>,
+			 <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>;
+		clock-names = "sdhci", "tmclk";
 		resets = <&tegra_car 15>;
 		reset-names = "sdhci";
 		pinctrl-names = "sdmmc-3v3-drv", "sdmmc-1v8-drv";
diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
index 9edfae5..24ef18f 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
@@ -417,10 +417,10 @@
 		ti,intr-trigger-type = <1>;
 		interrupt-controller;
 		interrupt-parent = <&gic500>;
-		#interrupt-cells = <2>;
+		#interrupt-cells = <1>;
 		ti,sci = <&dmsc>;
-		ti,sci-dst-id = <56>;
-		ti,sci-rm-range-girq = <0x1>;
+		ti,sci-dev-id = <100>;
+		ti,interrupt-ranges = <0 392 32>;
 	};
 
 	main_navss {
@@ -438,10 +438,11 @@
 			ti,intr-trigger-type = <4>;
 			interrupt-controller;
 			interrupt-parent = <&gic500>;
-			#interrupt-cells = <2>;
+			#interrupt-cells = <1>;
 			ti,sci = <&dmsc>;
-			ti,sci-dst-id = <56>;
-			ti,sci-rm-range-girq = <0x0>, <0x2>;
+			ti,sci-dev-id = <182>;
+			ti,interrupt-ranges = <0 64 64>,
+					      <64 448 64>;
 		};
 
 		inta_main_udmass: interrupt-controller@33d00000 {
@@ -452,8 +453,7 @@
 			msi-controller;
 			ti,sci = <&dmsc>;
 			ti,sci-dev-id = <179>;
-			ti,sci-rm-range-vint = <0x0>;
-			ti,sci-rm-range-global-event = <0x1>;
+			ti,interrupt-ranges = <0 0 256>;
 		};
 
 		secure_proxy_main: mailbox@32c00000 {
@@ -589,7 +589,7 @@
 				<0x0 0x33000000 0x0 0x40000>;
 			reg-names = "rt", "fifos", "proxy_gcfg", "proxy_target";
 			ti,num-rings = <818>;
-			ti,sci-rm-range-gp-rings = <0x2>; /* GP ring range */
+			ti,sci-rm-range-gp-rings = <0x1>; /* GP ring range */
 			ti,dma-ring-reset-quirk;
 			ti,sci = <&dmsc>;
 			ti,sci-dev-id = <187>;
@@ -609,11 +609,11 @@
 			ti,sci-dev-id = <188>;
 			ti,ringacc = <&ringacc>;
 
-			ti,sci-rm-range-tchan = <0x1>, /* TX_HCHAN */
-						<0x2>; /* TX_CHAN */
-			ti,sci-rm-range-rchan = <0x4>, /* RX_HCHAN */
-						<0x5>; /* RX_CHAN */
-			ti,sci-rm-range-rflow = <0x6>; /* GP RFLOW */
+			ti,sci-rm-range-tchan = <0xf>, /* TX_HCHAN */
+						<0xd>; /* TX_CHAN */
+			ti,sci-rm-range-rchan = <0xb>, /* RX_HCHAN */
+						<0xa>; /* RX_CHAN */
+			ti,sci-rm-range-rflow = <0x0>; /* GP RFLOW */
 		};
 
 		cpts@310d0000 {
@@ -622,7 +622,7 @@
 			reg-names = "cpts";
 			clocks = <&main_cpts_mux>;
 			clock-names = "cpts";
-			interrupts-extended = <&intr_main_navss 163 0>;
+			interrupts-extended = <&intr_main_navss 391>;
 			interrupt-names = "cpts";
 			ti,cpts-periodic-outputs = <6>;
 			ti,cpts-ext-ts-inputs = <8>;
@@ -645,8 +645,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&intr_main_gpio>;
-		interrupts = <57 256>, <57 257>, <57 258>, <57 259>, <57 260>,
-				<57 261>;
+		interrupts = <192>, <193>, <194>, <195>, <196>, <197>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <96>;
@@ -661,8 +660,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&intr_main_gpio>;
-		interrupts = <58 256>, <58 257>, <58 258>, <58 259>, <58 260>,
-				<58 261>;
+		interrupts = <200>, <201>, <202>, <203>, <204>, <205>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <90>;
diff --git a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
index 8c1abcf..51ca4b4 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
@@ -134,7 +134,7 @@
 				<0x0 0x2a500000 0x0 0x40000>;
 			reg-names = "rt", "fifos", "proxy_gcfg", "proxy_target";
 			ti,num-rings = <286>;
-			ti,sci-rm-range-gp-rings = <0x2>; /* GP ring range */
+			ti,sci-rm-range-gp-rings = <0x1>; /* GP ring range */
 			ti,dma-ring-reset-quirk;
 			ti,sci = <&dmsc>;
 			ti,sci-dev-id = <195>;
@@ -154,11 +154,11 @@
 			ti,sci-dev-id = <194>;
 			ti,ringacc = <&mcu_ringacc>;
 
-			ti,sci-rm-range-tchan = <0x1>, /* TX_HCHAN */
-						<0x2>; /* TX_CHAN */
-			ti,sci-rm-range-rchan = <0x3>, /* RX_HCHAN */
-						<0x4>; /* RX_CHAN */
-			ti,sci-rm-range-rflow = <0x5>; /* GP RFLOW */
+			ti,sci-rm-range-tchan = <0xf>, /* TX_HCHAN */
+						<0xd>; /* TX_CHAN */
+			ti,sci-rm-range-rchan = <0xb>, /* RX_HCHAN */
+						<0xa>; /* RX_CHAN */
+			ti,sci-rm-range-rflow = <0x0>; /* GP RFLOW */
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
index 5f55b9e..a1ffe88 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
@@ -74,10 +74,10 @@
 		ti,intr-trigger-type = <1>;
 		interrupt-controller;
 		interrupt-parent = <&gic500>;
-		#interrupt-cells = <2>;
+		#interrupt-cells = <1>;
 		ti,sci = <&dmsc>;
-		ti,sci-dst-id = <56>;
-		ti,sci-rm-range-girq = <0x4>;
+		ti,sci-dev-id = <156>;
+		ti,interrupt-ranges = <0 712 16>;
 	};
 
 	wkup_gpio0: wkup_gpio0@42110000 {
@@ -86,7 +86,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&intr_wkup_gpio>;
-		interrupts = <59 128>, <59 129>, <59 130>, <59 131>;
+		interrupts = <60>, <61>, <62>, <63>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <56>;
diff --git a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
index 611e662..b8a8a0fc 100644
--- a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
@@ -384,7 +384,7 @@
 };
 
 &mailbox0_cluster0 {
-	interrupts = <164 0>;
+	interrupts = <436>;
 
 	mbox_mcu_r5fss0_core0: mbox-mcu-r5fss0-core0 {
 		ti,mbox-tx = <1 0 0>;
@@ -393,7 +393,7 @@
 };
 
 &mailbox0_cluster1 {
-	interrupts = <165 0>;
+	interrupts = <432>;
 
 	mbox_mcu_r5fss0_core1: mbox-mcu-r5fss0-core1 {
 		ti,mbox-tx = <1 0 0>;
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
index 8bc1e6e..e8fc01d 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
@@ -287,7 +287,7 @@
 };
 
 &mailbox0_cluster0 {
-	interrupts = <214 0>;
+	interrupts = <436>;
 
 	mbox_mcu_r5fss0_core0: mbox-mcu-r5fss0-core0 {
 		ti,mbox-rx = <0 0 0>;
@@ -301,7 +301,7 @@
 };
 
 &mailbox0_cluster1 {
-	interrupts = <215 0>;
+	interrupts = <432>;
 
 	mbox_main_r5fss0_core0: mbox-main-r5fss0-core0 {
 		ti,mbox-rx = <0 0 0>;
@@ -315,7 +315,7 @@
 };
 
 &mailbox0_cluster2 {
-	interrupts = <216 0>;
+	interrupts = <428>;
 
 	mbox_main_r5fss1_core0: mbox-main-r5fss1-core0 {
 		ti,mbox-rx = <0 0 0>;
@@ -329,7 +329,7 @@
 };
 
 &mailbox0_cluster3 {
-	interrupts = <217 0>;
+	interrupts = <424>;
 
 	mbox_c66_0: mbox-c66-0 {
 		ti,mbox-rx = <0 0 0>;
@@ -343,7 +343,7 @@
 };
 
 &mailbox0_cluster4 {
-	interrupts = <218 0>;
+	interrupts = <420>;
 
 	mbox_c71_0: mbox-c71-0 {
 		ti,mbox-rx = <0 0 0>;
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
index d140602..12ceea9 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
@@ -80,10 +80,10 @@
 		ti,intr-trigger-type = <1>;
 		interrupt-controller;
 		interrupt-parent = <&gic500>;
-		#interrupt-cells = <2>;
+		#interrupt-cells = <1>;
 		ti,sci = <&dmsc>;
-		ti,sci-dst-id = <14>;
-		ti,sci-rm-range-girq = <0x1>;
+		ti,sci-dev-id = <131>;
+		ti,interrupt-ranges = <8 392 56>;
 	};
 
 	main_navss {
@@ -101,10 +101,12 @@
 			ti,intr-trigger-type = <4>;
 			interrupt-controller;
 			interrupt-parent = <&gic500>;
-			#interrupt-cells = <2>;
+			#interrupt-cells = <1>;
 			ti,sci = <&dmsc>;
-			ti,sci-dst-id = <14>;
-			ti,sci-rm-range-girq = <0>, <2>;
+			ti,sci-dev-id = <213>;
+			ti,interrupt-ranges = <0 64 64>,
+					      <64 448 64>,
+					      <128 672 64>;
 		};
 
 		main_udmass_inta: interrupt-controller@33d00000 {
@@ -115,8 +117,7 @@
 			msi-controller;
 			ti,sci = <&dmsc>;
 			ti,sci-dev-id = <209>;
-			ti,sci-rm-range-vint = <0xa>;
-			ti,sci-rm-range-global-event = <0xd>;
+			ti,interrupt-ranges = <0 0 256>;
 		};
 
 		secure_proxy_main: mailbox@32c00000 {
@@ -296,7 +297,7 @@
 			reg-names = "cpts";
 			clocks = <&k3_clks 201 1>;
 			clock-names = "cpts";
-			interrupts-extended = <&main_navss_intr 201 0>;
+			interrupts-extended = <&main_navss_intr 391>;
 			interrupt-names = "cpts";
 			ti,cpts-periodic-outputs = <6>;
 			ti,cpts-ext-ts-inputs = <8>;
@@ -688,8 +689,8 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <105 0>, <105 1>, <105 2>, <105 3>,
-			     <105 4>, <105 5>, <105 6>, <105 7>;
+		interrupts = <256>, <257>, <258>, <259>,
+			     <260>, <261>, <262>, <263>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <128>;
@@ -705,7 +706,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <106 0>, <106 1>, <106 2>;
+		interrupts = <288>, <289>, <290>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <36>;
@@ -721,8 +722,8 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <107 0>, <107 1>, <107 2>, <107 3>,
-			     <107 4>, <107 5>, <107 6>, <107 7>;
+		interrupts = <264>, <265>, <266>, <267>,
+			     <268>, <269>, <270>, <271>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <128>;
@@ -738,7 +739,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <108 0>, <108 1>, <108 2>;
+		interrupts = <292>, <293>, <294>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <36>;
@@ -754,8 +755,8 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <109 0>, <109 1>, <109 2>, <109 3>,
-			     <109 4>, <109 5>, <109 6>, <109 7>;
+		interrupts = <272>, <273>, <274>, <275>,
+			     <276>, <277>, <278>, <279>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <128>;
@@ -771,7 +772,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <110 0>, <110 1>, <110 2>;
+		interrupts = <296>, <297>, <298>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <36>;
@@ -787,8 +788,8 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <111 0>, <111 1>, <111 2>, <111 3>,
-			     <111 4>, <111 5>, <111 6>, <111 7>;
+		interrupts = <280>, <281>, <282>, <283>,
+			     <284>, <285>, <286>, <287>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <128>;
@@ -804,7 +805,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&main_gpio_intr>;
-		interrupts = <112 0>, <112 1>, <112 2>;
+		interrupts = <300>, <301>, <302>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <36>;
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
index 30a735b..c4a48e8 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
@@ -101,10 +101,10 @@
 		ti,intr-trigger-type = <1>;
 		interrupt-controller;
 		interrupt-parent = <&gic500>;
-		#interrupt-cells = <2>;
+		#interrupt-cells = <1>;
 		ti,sci = <&dmsc>;
-		ti,sci-dst-id = <14>;
-		ti,sci-rm-range-girq = <0x5>;
+		ti,sci-dev-id = <137>;
+		ti,interrupt-ranges = <16 960 16>;
 	};
 
 	wkup_gpio0: gpio@42110000 {
@@ -113,8 +113,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&wkup_gpio_intr>;
-		interrupts = <113 0>, <113 1>, <113 2>,
-			     <113 3>, <113 4>, <113 5>;
+		interrupts = <103>, <104>, <105>, <106>, <107>, <108>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <84>;
@@ -130,8 +129,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-parent = <&wkup_gpio_intr>;
-		interrupts = <114 0>, <114 1>, <114 2>,
-			     <114 3>, <114 4>, <114 5>;
+		interrupts = <112>, <113>, <114>, <115>, <116>, <117>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,ngpio = <84>;
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index 9174ddc..3ec99f1 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -13,6 +13,7 @@
  */
 
 #include <dt-bindings/power/xlnx-zynqmp-power.h>
+#include <dt-bindings/reset/xlnx-zynqmp-resets.h>
 
 / {
 	compatible = "xlnx,zynqmp";
@@ -558,6 +559,15 @@
 			};
 		};
 
+		psgtr: phy@fd400000 {
+			compatible = "xlnx,zynqmp-psgtr-v1.1";
+			status = "disabled";
+			reg = <0x0 0xfd400000 0x0 0x40000>,
+			      <0x0 0xfd3d0000 0x0 0x1000>;
+			reg-names = "serdes", "siou";
+			#phy-cells = <4>;
+		};
+
 		rtc: rtc@ffa60000 {
 			compatible = "xlnx,zynqmp-rtc";
 			status = "disabled";
@@ -601,7 +611,7 @@
 			power-domains = <&zynqmp_firmware PD_SD_1>;
 		};
 
-		smmu: smmu@fd800000 {
+		smmu: iommu@fd800000 {
 			compatible = "arm,mmu-500";
 			reg = <0x0 0xfd800000 0x0 0x20000>;
 			status = "disabled";
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index e0f3382..6d04b95 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -724,6 +724,17 @@
 CONFIG_USB_RENESAS_USBHS_UDC=m
 CONFIG_USB_RENESAS_USB3=m
 CONFIG_USB_TEGRA_XUDC=m
+CONFIG_USB_CONFIGFS=m
+CONFIG_USB_CONFIGFS_SERIAL=y
+CONFIG_USB_CONFIGFS_ACM=y
+CONFIG_USB_CONFIGFS_OBEX=y
+CONFIG_USB_CONFIGFS_NCM=y
+CONFIG_USB_CONFIGFS_ECM=y
+CONFIG_USB_CONFIGFS_ECM_SUBSET=y
+CONFIG_USB_CONFIGFS_RNDIS=y
+CONFIG_USB_CONFIGFS_EEM=y
+CONFIG_USB_CONFIGFS_MASS_STORAGE=y
+CONFIG_USB_CONFIGFS_F_FS=y
 CONFIG_TYPEC=m
 CONFIG_TYPEC_TCPM=m
 CONFIG_TYPEC_FUSB302=m
@@ -914,6 +925,7 @@
 CONFIG_ARCH_K3_AM6_SOC=y
 CONFIG_ARCH_K3_J721E_SOC=y
 CONFIG_TI_SCI_PM_DOMAINS=y
+CONFIG_EXTCON_PTN5150=m
 CONFIG_EXTCON_USB_GPIO=y
 CONFIG_EXTCON_USBC_CROS_EC=y
 CONFIG_IIO=y
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index b357164..63a52ad 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -788,7 +788,7 @@
 
 0:	mov		bskey, x21
 	mov		rounds, x22
-	br		x7
+	br		x16
 SYM_FUNC_END(__xts_crypt8)
 
 	.macro		__xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
@@ -806,7 +806,7 @@
 	uzp1		v30.4s, v30.4s, v25.4s
 	ld1		{v25.16b}, [x24]
 
-99:	adr		x7, \do8
+99:	adr		x16, \do8
 	bl		__xts_crypt8
 
 	ldp		q16, q17, [sp, #.Lframe_local_offset]
diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h
index 44209f6..ffb1a40 100644
--- a/arch/arm64/include/asm/archrandom.h
+++ b/arch/arm64/include/asm/archrandom.h
@@ -79,10 +79,5 @@
 }
 #define arch_get_random_seed_long_early arch_get_random_seed_long_early
 
-#else
-
-static inline bool __arm64_rndr(unsigned long *v) { return false; }
-static inline bool __init __early_cpu_has_rndr(void) { return false; }
-
 #endif /* CONFIG_ARCH_RANDOM */
 #endif /* _ASM_ARCHRANDOM_H */
diff --git a/arch/arm64/include/asm/boot.h b/arch/arm64/include/asm/boot.h
index c7f67da..3e7943f 100644
--- a/arch/arm64/include/asm/boot.h
+++ b/arch/arm64/include/asm/boot.h
@@ -13,8 +13,7 @@
 #define MAX_FDT_SIZE		SZ_2M
 
 /*
- * arm64 requires the kernel image to placed
- * TEXT_OFFSET bytes beyond a 2 MB aligned base
+ * arm64 requires the kernel image to placed at a 2 MB aligned base address
  */
 #define MIN_KIMG_ALIGN		SZ_2M
 
diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h
index 51a7ce8..6fb2e6b 100644
--- a/arch/arm64/include/asm/compiler.h
+++ b/arch/arm64/include/asm/compiler.h
@@ -2,6 +2,12 @@
 #ifndef __ASM_COMPILER_H
 #define __ASM_COMPILER_H
 
+#ifdef ARM64_ASM_ARCH
+#define ARM64_ASM_PREAMBLE ".arch " ARM64_ASM_ARCH "\n"
+#else
+#define ARM64_ASM_PREAMBLE
+#endif
+
 /*
  * The EL0/EL1 pointer bits used by a pointer authentication code.
  * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply.
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index d28e8f3..e95c4df 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -21,7 +21,7 @@
  *		mechanism for doing so, tests whether it is possible to boot
  *		the given CPU.
  * @cpu_boot:	Boots a cpu into the kernel.
- * @cpu_postboot: Optionally, perform any post-boot cleanup or necesary
+ * @cpu_postboot: Optionally, perform any post-boot cleanup or necessary
  *		synchronisation. Called from the cpu being booted.
  * @cpu_can_disable: Determines whether a CPU can be disabled based on
  *		mechanism-specific information.
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 07b643a..42868db 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -31,13 +31,13 @@
 #define ARM64_HAS_DCPOP				21
 #define ARM64_SVE				22
 #define ARM64_UNMAP_KERNEL_AT_EL0		23
-#define ARM64_HARDEN_BRANCH_PREDICTOR		24
+#define ARM64_SPECTRE_V2			24
 #define ARM64_HAS_RAS_EXTN			25
 #define ARM64_WORKAROUND_843419			26
 #define ARM64_HAS_CACHE_IDC			27
 #define ARM64_HAS_CACHE_DIC			28
 #define ARM64_HW_DBM				29
-#define ARM64_SSBD				30
+#define ARM64_SPECTRE_V4			30
 #define ARM64_MISMATCHED_CACHE_TYPE		31
 #define ARM64_HAS_STAGE2_FWB			32
 #define ARM64_HAS_CRC32				33
@@ -64,7 +64,8 @@
 #define ARM64_BTI				54
 #define ARM64_HAS_ARMv8_4_TTL			55
 #define ARM64_HAS_TLB_RANGE			56
+#define ARM64_MTE				57
 
-#define ARM64_NCAPS				57
+#define ARM64_NCAPS				58
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 89b4f01..f7e7144 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -358,7 +358,7 @@
 }
 
 /*
- * Generic helper for handling capabilties with multiple (match,enable) pairs
+ * Generic helper for handling capabilities with multiple (match,enable) pairs
  * of call backs, sharing the same capability bit.
  * Iterate over each entry to see if at least one matches.
  */
@@ -681,6 +681,12 @@
 	       cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);
 }
 
+static inline bool system_supports_mte(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_MTE) &&
+		cpus_have_const_cap(ARM64_MTE);
+}
+
 static inline bool system_has_prio_mask_debugging(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING) &&
@@ -698,30 +704,6 @@
 		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
 }
 
-#define ARM64_BP_HARDEN_UNKNOWN		-1
-#define ARM64_BP_HARDEN_WA_NEEDED	0
-#define ARM64_BP_HARDEN_NOT_REQUIRED	1
-
-int get_spectre_v2_workaround_state(void);
-
-#define ARM64_SSBD_UNKNOWN		-1
-#define ARM64_SSBD_FORCE_DISABLE	0
-#define ARM64_SSBD_KERNEL		1
-#define ARM64_SSBD_FORCE_ENABLE		2
-#define ARM64_SSBD_MITIGATED		3
-
-static inline int arm64_get_ssbd_state(void)
-{
-#ifdef CONFIG_ARM64_SSBD
-	extern int ssbd_state;
-	return ssbd_state;
-#else
-	return ARM64_SSBD_UNKNOWN;
-#endif
-}
-
-void arm64_set_ssbd_mitigation(bool state);
-
 extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 
 static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 035003a..22c81f1 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -35,7 +35,9 @@
 #define ESR_ELx_EC_SYS64	(0x18)
 #define ESR_ELx_EC_SVE		(0x19)
 #define ESR_ELx_EC_ERET		(0x1a)	/* EL2 only */
-/* Unallocated EC: 0x1b - 0x1E */
+/* Unallocated EC: 0x1B */
+#define ESR_ELx_EC_FPAC		(0x1C)	/* EL1 and above */
+/* Unallocated EC: 0x1D - 0x1E */
 #define ESR_ELx_EC_IMP_DEF	(0x1f)	/* EL3 only */
 #define ESR_ELx_EC_IABT_LOW	(0x20)
 #define ESR_ELx_EC_IABT_CUR	(0x21)
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 7577a75..99b9383 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -47,4 +47,5 @@
 void do_cp15instr(unsigned int esr, struct pt_regs *regs);
 void do_el0_svc(struct pt_regs *regs);
 void do_el0_svc_compat(struct pt_regs *regs);
+void do_ptrauth_fault(struct pt_regs *regs, unsigned int esr);
 #endif	/* __ASM_EXCEPTION_H */
diff --git a/arch/arm64/include/asm/extable.h b/arch/arm64/include/asm/extable.h
index 840a35e..b15eb4a 100644
--- a/arch/arm64/include/asm/extable.h
+++ b/arch/arm64/include/asm/extable.h
@@ -22,6 +22,15 @@
 
 #define ARCH_HAS_RELATIVE_EXTABLE
 
+static inline bool in_bpf_jit(struct pt_regs *regs)
+{
+	if (!IS_ENABLED(CONFIG_BPF_JIT))
+		return false;
+
+	return regs->pc >= BPF_JIT_REGION_START &&
+	       regs->pc < BPF_JIT_REGION_END;
+}
+
 #ifdef CONFIG_BPF_JIT
 int arm64_bpf_fixup_exception(const struct exception_table_entry *ex,
 			      struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 59f10dd..bec5f14 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -69,6 +69,9 @@
 extern void sve_save_state(void *state, u32 *pfpsr);
 extern void sve_load_state(void const *state, u32 const *pfpsr,
 			   unsigned long vq_minus_1);
+extern void sve_flush_live(void);
+extern void sve_load_from_fpsimd_state(struct user_fpsimd_state const *state,
+				       unsigned long vq_minus_1);
 extern unsigned int sve_get_vl(void);
 
 struct arm64_cpu_capabilities;
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index 636e9d9..af43367 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -164,25 +164,59 @@
 		| ((\np) << 5)
 .endm
 
+/* PFALSE P\np.B */
+.macro _sve_pfalse np
+	_sve_check_preg \np
+	.inst	0x2518e400			\
+		| (\np)
+.endm
+
 .macro __for from:req, to:req
 	.if (\from) == (\to)
-		_for__body \from
+		_for__body %\from
 	.else
-		__for \from, (\from) + ((\to) - (\from)) / 2
-		__for (\from) + ((\to) - (\from)) / 2 + 1, \to
+		__for %\from, %((\from) + ((\to) - (\from)) / 2)
+		__for %((\from) + ((\to) - (\from)) / 2 + 1), %\to
 	.endif
 .endm
 
 .macro _for var:req, from:req, to:req, insn:vararg
 	.macro _for__body \var:req
+		.noaltmacro
 		\insn
+		.altmacro
 	.endm
 
+	.altmacro
 	__for \from, \to
+	.noaltmacro
 
 	.purgem _for__body
 .endm
 
+/* Update ZCR_EL1.LEN with the new VQ */
+.macro sve_load_vq xvqminus1, xtmp, xtmp2
+		mrs_s		\xtmp, SYS_ZCR_EL1
+		bic		\xtmp2, \xtmp, ZCR_ELx_LEN_MASK
+		orr		\xtmp2, \xtmp2, \xvqminus1
+		cmp		\xtmp2, \xtmp
+		b.eq		921f
+		msr_s		SYS_ZCR_EL1, \xtmp2	//self-synchronising
+921:
+.endm
+
+/* Preserve the first 128-bits of Znz and zero the rest. */
+.macro _sve_flush_z nz
+	_sve_check_zreg \nz
+	mov	v\nz\().16b, v\nz\().16b
+.endm
+
+.macro sve_flush
+ _for n, 0, 31, _sve_flush_z	\n
+ _for n, 0, 15, _sve_pfalse	\n
+		_sve_wrffr	0
+.endm
+
 .macro sve_save nxbase, xpfpsr, nxtmp
  _for n, 0, 31,	_sve_str_v	\n, \nxbase, \n - 34
  _for n, 0, 15,	_sve_str_p	\n, \nxbase, \n - 16
@@ -197,13 +231,7 @@
 .endm
 
 .macro sve_load nxbase, xpfpsr, xvqminus1, nxtmp, xtmp2
-		mrs_s		x\nxtmp, SYS_ZCR_EL1
-		bic		\xtmp2, x\nxtmp, ZCR_ELx_LEN_MASK
-		orr		\xtmp2, \xtmp2, \xvqminus1
-		cmp		\xtmp2, x\nxtmp
-		b.eq		921f
-		msr_s		SYS_ZCR_EL1, \xtmp2	// self-synchronising
-921:
+		sve_load_vq	\xvqminus1, x\nxtmp, \xtmp2
  _for n, 0, 31,	_sve_ldr_v	\n, \nxbase, \n - 34
 		_sve_ldr_p	0, \nxbase
 		_sve_wrffr	0
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 22f73fe..9a5498c 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -8,18 +8,27 @@
 #include <uapi/asm/hwcap.h>
 #include <asm/cpufeature.h>
 
+#define COMPAT_HWCAP_SWP	(1 << 0)
 #define COMPAT_HWCAP_HALF	(1 << 1)
 #define COMPAT_HWCAP_THUMB	(1 << 2)
+#define COMPAT_HWCAP_26BIT	(1 << 3)
 #define COMPAT_HWCAP_FAST_MULT	(1 << 4)
+#define COMPAT_HWCAP_FPA	(1 << 5)
 #define COMPAT_HWCAP_VFP	(1 << 6)
 #define COMPAT_HWCAP_EDSP	(1 << 7)
+#define COMPAT_HWCAP_JAVA	(1 << 8)
+#define COMPAT_HWCAP_IWMMXT	(1 << 9)
+#define COMPAT_HWCAP_CRUNCH	(1 << 10)
+#define COMPAT_HWCAP_THUMBEE	(1 << 11)
 #define COMPAT_HWCAP_NEON	(1 << 12)
 #define COMPAT_HWCAP_VFPv3	(1 << 13)
+#define COMPAT_HWCAP_VFPV3D16	(1 << 14)
 #define COMPAT_HWCAP_TLS	(1 << 15)
 #define COMPAT_HWCAP_VFPv4	(1 << 16)
 #define COMPAT_HWCAP_IDIVA	(1 << 17)
 #define COMPAT_HWCAP_IDIVT	(1 << 18)
 #define COMPAT_HWCAP_IDIV	(COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
+#define COMPAT_HWCAP_VFPD32	(1 << 19)
 #define COMPAT_HWCAP_LPAE	(1 << 20)
 #define COMPAT_HWCAP_EVTSTRM	(1 << 21)
 
@@ -95,7 +104,7 @@
 #define KERNEL_HWCAP_DGH		__khwcap2_feature(DGH)
 #define KERNEL_HWCAP_RNG		__khwcap2_feature(RNG)
 #define KERNEL_HWCAP_BTI		__khwcap2_feature(BTI)
-/* reserved for KERNEL_HWCAP_MTE	__khwcap2_feature(MTE) */
+#define KERNEL_HWCAP_MTE		__khwcap2_feature(MTE)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 0bc4614..4b39293d 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -359,9 +359,13 @@
 __AARCH64_INSN_FUNCS(exception,	0xFF000000, 0xD4000000)
 __AARCH64_INSN_FUNCS(hint,	0xFFFFF01F, 0xD503201F)
 __AARCH64_INSN_FUNCS(br,	0xFFFFFC1F, 0xD61F0000)
+__AARCH64_INSN_FUNCS(br_auth,	0xFEFFF800, 0xD61F0800)
 __AARCH64_INSN_FUNCS(blr,	0xFFFFFC1F, 0xD63F0000)
+__AARCH64_INSN_FUNCS(blr_auth,	0xFEFFF800, 0xD63F0800)
 __AARCH64_INSN_FUNCS(ret,	0xFFFFFC1F, 0xD65F0000)
+__AARCH64_INSN_FUNCS(ret_auth,	0xFFFFFBFF, 0xD65F0BFF)
 __AARCH64_INSN_FUNCS(eret,	0xFFFFFFFF, 0xD69F03E0)
+__AARCH64_INSN_FUNCS(eret_auth,	0xFFFFFBFF, 0xD69F0BFF)
 __AARCH64_INSN_FUNCS(mrs,	0xFFF00000, 0xD5300000)
 __AARCH64_INSN_FUNCS(msr_imm,	0xFFF8F01F, 0xD500401F)
 __AARCH64_INSN_FUNCS(msr_reg,	0xFFF00000, 0xD5100000)
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index aa4b652..ff328e5b 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -95,6 +95,11 @@
 	return res;
 }
 
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
 static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags;
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 329fb15..19ca76e 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -86,7 +86,7 @@
 			+ EARLY_PGDS((vstart), (vend)) 	/* each PGDIR needs a next level page table */	\
 			+ EARLY_PUDS((vstart), (vend))	/* each PUD needs a next level page table */	\
 			+ EARLY_PMDS((vstart), (vend)))	/* each PMD needs a next level page table */
-#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR + TEXT_OFFSET, _end))
+#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end))
 #define IDMAP_DIR_SIZE		(IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
 
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 51c1d99..64ce293 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -12,6 +12,7 @@
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
+#define HCR_ATA		(UL(1) << 56)
 #define HCR_FWB		(UL(1) << 46)
 #define HCR_API		(UL(1) << 41)
 #define HCR_APK		(UL(1) << 40)
@@ -66,18 +67,19 @@
  * TWI:		Trap WFI
  * TIDCP:	Trap L2CTLR/L2ECTLR
  * BSU_IS:	Upgrade barriers to the inner shareable domain
- * FB:		Force broadcast of all maintainance operations
+ * FB:		Force broadcast of all maintenance operations
  * AMO:		Override CPSR.A and enable signaling with VA
  * IMO:		Override CPSR.I and enable signaling with VI
  * FMO:		Override CPSR.F and enable signaling with VF
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
+ * PTW:		Take a stage2 fault if a stage1 walk steps in device memory
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
 			 HCR_BSU_IS | HCR_FB | HCR_TAC | \
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
-			 HCR_FMO | HCR_IMO)
+			 HCR_FMO | HCR_IMO | HCR_PTW )
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
-#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK)
+#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index fb1a922..7f7072f 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -9,9 +9,6 @@
 
 #include <asm/virt.h>
 
-#define	VCPU_WORKAROUND_2_FLAG_SHIFT	0
-#define	VCPU_WORKAROUND_2_FLAG		(_AC(1, UL) << VCPU_WORKAROUND_2_FLAG_SHIFT)
-
 #define ARM_EXIT_WITH_SERROR_BIT  31
 #define ARM_EXCEPTION_CODE(x)	  ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT))
 #define ARM_EXCEPTION_IS_TRAP(x)  (ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_TRAP)
@@ -102,11 +99,9 @@
 #define __kvm_hyp_init		CHOOSE_NVHE_SYM(__kvm_hyp_init)
 #define __kvm_hyp_vector	CHOOSE_HYP_SYM(__kvm_hyp_vector)
 
-#ifdef CONFIG_KVM_INDIRECT_VECTORS
 extern atomic_t arm64_el2_vector_last_slot;
 DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #define __bp_harden_hyp_vecs	CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
-#endif
 
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
@@ -169,6 +164,34 @@
 		*__hyp_this_cpu_ptr(sym);				\
 	 })
 
+#define __KVM_EXTABLE(from, to)						\
+	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
+	"	.align		3\n"					\
+	"	.long		(" #from " - .), (" #to " - .)\n"	\
+	"	.popsection\n"
+
+
+#define __kvm_at(at_op, addr)						\
+( { 									\
+	int __kvm_at_err = 0;						\
+	u64 spsr, elr;							\
+	asm volatile(							\
+	"	mrs	%1, spsr_el2\n"					\
+	"	mrs	%2, elr_el2\n"					\
+	"1:	at	"at_op", %3\n"					\
+	"	isb\n"							\
+	"	b	9f\n"						\
+	"2:	msr	spsr_el2, %1\n"					\
+	"	msr	elr_el2, %2\n"					\
+	"	mov	%w0, %4\n"					\
+	"9:\n"								\
+	__KVM_EXTABLE(1b, 2b)						\
+	: "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr)		\
+	: "r" (addr), "i" (-EFAULT));					\
+	__kvm_at_err;							\
+} )
+
+
 #else /* __ASSEMBLY__ */
 
 .macro hyp_adr_this_cpu reg, sym, tmp
@@ -193,6 +216,21 @@
 	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
 .endm
 
+/*
+ * KVM extable for unexpected exceptions.
+ * In the same format _asm_extable, but output to a different section so that
+ * it can be mapped to EL2. The KVM version is not sorted. The caller must
+ * ensure:
+ * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented
+ * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup.
+ */
+.macro	_kvm_extable, from, to
+	.pushsection	__kvm_ex_table, "a"
+	.align		3
+	.long		(\from - .), (\to - .)
+	.popsection
+.endm
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 49a55be..5ef2669 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -298,15 +298,15 @@
 	return (kvm_vcpu_get_esr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
 }
 
-static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW);
 }
 
+/* Always check for S1PTW *before* using this. */
 static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR) ||
-		kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR;
 }
 
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
@@ -335,6 +335,11 @@
 	return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW;
 }
 
+static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu);
+}
+
 static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
@@ -372,6 +377,9 @@
 
 static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 {
+	if (kvm_vcpu_abt_iss1tw(vcpu))
+		return true;
+
 	if (kvm_vcpu_trap_is_iabt(vcpu))
 		return false;
 
@@ -383,20 +391,6 @@
 	return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
 }
 
-static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG;
-}
-
-static inline void kvm_arm_set_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu,
-						      bool flag)
-{
-	if (flag)
-		vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;
-	else
-		vcpu->arch.workaround_flags &= ~VCPU_WORKAROUND_2_FLAG;
-}
-
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu)) {
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 65568b2..bb5e5b8 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -368,7 +368,6 @@
 
 	/* Guest PV state */
 	struct {
-		u64 steal;
 		u64 last_steal;
 		gpa_t base;
 	} steal;
@@ -473,7 +472,7 @@
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva_range(struct kvm *kvm,
-			unsigned long start, unsigned long end);
+			unsigned long start, unsigned long end, unsigned flags);
 int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
@@ -544,6 +543,7 @@
 gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu);
 
+bool kvm_arm_pvtime_supported(void);
 int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
@@ -631,46 +631,6 @@
 static inline void kvm_clr_pmu_events(u32 clr) {}
 #endif
 
-#define KVM_BP_HARDEN_UNKNOWN		-1
-#define KVM_BP_HARDEN_WA_NEEDED		0
-#define KVM_BP_HARDEN_NOT_REQUIRED	1
-
-static inline int kvm_arm_harden_branch_predictor(void)
-{
-	switch (get_spectre_v2_workaround_state()) {
-	case ARM64_BP_HARDEN_WA_NEEDED:
-		return KVM_BP_HARDEN_WA_NEEDED;
-	case ARM64_BP_HARDEN_NOT_REQUIRED:
-		return KVM_BP_HARDEN_NOT_REQUIRED;
-	case ARM64_BP_HARDEN_UNKNOWN:
-	default:
-		return KVM_BP_HARDEN_UNKNOWN;
-	}
-}
-
-#define KVM_SSBD_UNKNOWN		-1
-#define KVM_SSBD_FORCE_DISABLE		0
-#define KVM_SSBD_KERNEL		1
-#define KVM_SSBD_FORCE_ENABLE		2
-#define KVM_SSBD_MITIGATED		3
-
-static inline int kvm_arm_have_ssbd(void)
-{
-	switch (arm64_get_ssbd_state()) {
-	case ARM64_SSBD_FORCE_DISABLE:
-		return KVM_SSBD_FORCE_DISABLE;
-	case ARM64_SSBD_KERNEL:
-		return KVM_SSBD_KERNEL;
-	case ARM64_SSBD_FORCE_ENABLE:
-		return KVM_SSBD_FORCE_ENABLE;
-	case ARM64_SSBD_MITIGATED:
-		return KVM_SSBD_MITIGATED;
-	case ARM64_SSBD_UNKNOWN:
-	default:
-		return KVM_SSBD_UNKNOWN;
-	}
-}
-
 void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
 void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 189839c..cff1ceb 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -9,6 +9,7 @@
 
 #include <asm/page.h>
 #include <asm/memory.h>
+#include <asm/mmu.h>
 #include <asm/cpufeature.h>
 
 /*
@@ -430,19 +431,17 @@
 	return ret;
 }
 
-#ifdef CONFIG_KVM_INDIRECT_VECTORS
 /*
  * EL2 vectors can be mapped and rerouted in a number of ways,
  * depending on the kernel configuration and CPU present:
  *
- * - If the CPU has the ARM64_HARDEN_BRANCH_PREDICTOR cap, the
- *   hardening sequence is placed in one of the vector slots, which is
- *   executed before jumping to the real vectors.
+ * - If the CPU is affected by Spectre-v2, the hardening sequence is
+ *   placed in one of the vector slots, which is executed before jumping
+ *   to the real vectors.
  *
- * - If the CPU has both the ARM64_HARDEN_EL2_VECTORS cap and the
- *   ARM64_HARDEN_BRANCH_PREDICTOR cap, the slot containing the
- *   hardening sequence is mapped next to the idmap page, and executed
- *   before jumping to the real vectors.
+ * - If the CPU also has the ARM64_HARDEN_EL2_VECTORS cap, the slot
+ *   containing the hardening sequence is mapped next to the idmap page,
+ *   and executed before jumping to the real vectors.
  *
  * - If the CPU only has the ARM64_HARDEN_EL2_VECTORS cap, then an
  *   empty slot is selected, mapped next to the idmap page, and
@@ -452,19 +451,16 @@
  * VHE, as we don't have hypervisor-specific mappings. If the system
  * is VHE and yet selects this capability, it will be ignored.
  */
-#include <asm/mmu.h>
-
 extern void *__kvm_bp_vect_base;
 extern int __kvm_harden_el2_vector_slot;
 
-/*  This is called on both VHE and !VHE systems */
 static inline void *kvm_get_hyp_vector(void)
 {
 	struct bp_hardening_data *data = arm64_get_bp_hardening_data();
 	void *vect = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
 	int slot = -1;
 
-	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) && data->fn) {
+	if (cpus_have_const_cap(ARM64_SPECTRE_V2) && data->fn) {
 		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs));
 		slot = data->hyp_vectors_slot;
 	}
@@ -481,76 +477,6 @@
 	return vect;
 }
 
-/*  This is only called on a !VHE system */
-static inline int kvm_map_vectors(void)
-{
-	/*
-	 * HBP  = ARM64_HARDEN_BRANCH_PREDICTOR
-	 * HEL2 = ARM64_HARDEN_EL2_VECTORS
-	 *
-	 * !HBP + !HEL2 -> use direct vectors
-	 *  HBP + !HEL2 -> use hardened vectors in place
-	 * !HBP +  HEL2 -> allocate one vector slot and use exec mapping
-	 *  HBP +  HEL2 -> use hardened vertors and use exec mapping
-	 */
-	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR)) {
-		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs);
-		__kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base);
-	}
-
-	if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) {
-		phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs);
-		unsigned long size = __BP_HARDEN_HYP_VECS_SZ;
-
-		/*
-		 * Always allocate a spare vector slot, as we don't
-		 * know yet which CPUs have a BP hardening slot that
-		 * we can reuse.
-		 */
-		__kvm_harden_el2_vector_slot = atomic_inc_return(&arm64_el2_vector_last_slot);
-		BUG_ON(__kvm_harden_el2_vector_slot >= BP_HARDEN_EL2_SLOTS);
-		return create_hyp_exec_mappings(vect_pa, size,
-						&__kvm_bp_vect_base);
-	}
-
-	return 0;
-}
-#else
-static inline void *kvm_get_hyp_vector(void)
-{
-	return kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
-}
-
-static inline int kvm_map_vectors(void)
-{
-	return 0;
-}
-#endif
-
-#ifdef CONFIG_ARM64_SSBD
-DECLARE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);
-
-static inline int hyp_map_aux_data(void)
-{
-	int cpu, err;
-
-	for_each_possible_cpu(cpu) {
-		u64 *ptr;
-
-		ptr = per_cpu_ptr(&arm64_ssbd_callback_required, cpu);
-		err = create_hyp_mappings(ptr, ptr + 1, PAGE_HYP);
-		if (err)
-			return err;
-	}
-	return 0;
-}
-#else
-static inline int hyp_map_aux_data(void)
-{
-	return 0;
-}
-#endif
-
 #define kvm_phys_to_vttbr(addr)		phys_to_ttbr(addr)
 
 /*
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index afa7225..43640d7 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -126,13 +126,18 @@
 
 /*
  * Memory types available.
+ *
+ * IMPORTANT: MT_NORMAL must be index 0 since vm_get_page_prot() may 'or' in
+ *	      the MT_NORMAL_TAGGED memory type for PROT_MTE mappings. Note
+ *	      that protection_map[] only contains MT_NORMAL attributes.
  */
-#define MT_DEVICE_nGnRnE	0
-#define MT_DEVICE_nGnRE		1
-#define MT_DEVICE_GRE		2
-#define MT_NORMAL_NC		3
-#define MT_NORMAL		4
-#define MT_NORMAL_WT		5
+#define MT_NORMAL		0
+#define MT_NORMAL_TAGGED	1
+#define MT_NORMAL_NC		2
+#define MT_NORMAL_WT		3
+#define MT_DEVICE_nGnRnE	4
+#define MT_DEVICE_nGnRE		5
+#define MT_DEVICE_GRE		6
 
 /*
  * Memory types for Stage-2 translation
@@ -169,7 +174,7 @@
 /* PHYS_OFFSET - the physical address of the start of memory. */
 #define PHYS_OFFSET		({ VM_BUG_ON(memstart_addr & 1); memstart_addr; })
 
-/* the virtual base of the kernel image (minus TEXT_OFFSET) */
+/* the virtual base of the kernel image */
 extern u64			kimage_vaddr;
 
 /* the offset between the kernel virtual and physical mappings */
diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
index 081ec8d..e3e28f7 100644
--- a/arch/arm64/include/asm/mman.h
+++ b/arch/arm64/include/asm/mman.h
@@ -9,16 +9,53 @@
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 	unsigned long pkey __always_unused)
 {
-	if (system_supports_bti() && (prot & PROT_BTI))
-		return VM_ARM64_BTI;
+	unsigned long ret = 0;
 
-	return 0;
+	if (system_supports_bti() && (prot & PROT_BTI))
+		ret |= VM_ARM64_BTI;
+
+	if (system_supports_mte() && (prot & PROT_MTE))
+		ret |= VM_MTE;
+
+	return ret;
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
+static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+{
+	/*
+	 * Only allow MTE on anonymous mappings as these are guaranteed to be
+	 * backed by tags-capable memory. The vm_flags may be overridden by a
+	 * filesystem supporting MTE (RAM-based).
+	 */
+	if (system_supports_mte() && (flags & MAP_ANONYMOUS))
+		return VM_MTE_ALLOWED;
+
+	return 0;
+}
+#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+
 static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
 {
-	return (vm_flags & VM_ARM64_BTI) ? __pgprot(PTE_GP) : __pgprot(0);
+	pteval_t prot = 0;
+
+	if (vm_flags & VM_ARM64_BTI)
+		prot |= PTE_GP;
+
+	/*
+	 * There are two conditions required for returning a Normal Tagged
+	 * memory type: (1) the user requested it via PROT_MTE passed to
+	 * mmap() or mprotect() and (2) the corresponding vma supports MTE. We
+	 * register (1) as VM_MTE in the vma->vm_flags and (2) as
+	 * VM_MTE_ALLOWED. Note that the latter can only be set during the
+	 * mmap() call since mprotect() does not accept MAP_* flags.
+	 * Checking for VM_MTE only is sufficient since arch_validate_flags()
+	 * does not permit (VM_MTE & !VM_MTE_ALLOWED).
+	 */
+	if (vm_flags & VM_MTE)
+		prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED);
+
+	return __pgprot(prot);
 }
 #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
 
@@ -30,8 +67,21 @@
 	if (system_supports_bti())
 		supported |= PROT_BTI;
 
+	if (system_supports_mte())
+		supported |= PROT_MTE;
+
 	return (prot & ~supported) == 0;
 }
 #define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr)
 
+static inline bool arch_validate_flags(unsigned long vm_flags)
+{
+	if (!system_supports_mte())
+		return true;
+
+	/* only allow VM_MTE if VM_MTE_ALLOWED has been set previously */
+	return !(vm_flags & VM_MTE) || (vm_flags & VM_MTE_ALLOWED);
+}
+#define arch_validate_flags(vm_flags) arch_validate_flags(vm_flags)
+
 #endif /* ! __ASM_MMAN_H__ */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index a7a5eca..b2e91c1 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -17,11 +17,14 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/refcount.h>
+
 typedef struct {
 	atomic64_t	id;
 #ifdef CONFIG_COMPAT
 	void		*sigpage;
 #endif
+	refcount_t	pinned;
 	void		*vdso;
 	unsigned long	flags;
 } mm_context_t;
@@ -45,7 +48,6 @@
 	bp_hardening_cb_t	fn;
 };
 
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
 static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
@@ -57,21 +59,13 @@
 {
 	struct bp_hardening_data *d;
 
-	if (!cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR))
+	if (!cpus_have_const_cap(ARM64_SPECTRE_V2))
 		return;
 
 	d = arm64_get_bp_hardening_data();
 	if (d->fn)
 		d->fn();
 }
-#else
-static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
-{
-	return NULL;
-}
-
-static inline void arm64_apply_bp_hardening(void)	{ }
-#endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
 
 extern void arm64_memblock_init(void);
 extern void paging_init(void);
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index f2d7537..0672236 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -177,7 +177,13 @@
 #define destroy_context(mm)		do { } while(0)
 void check_and_switch_context(struct mm_struct *mm);
 
-#define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
+static inline int
+init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+	atomic64_set(&mm->context.id, 0);
+	refcount_set(&mm->context.pinned, 0);
+	return 0;
+}
 
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 static inline void update_saved_ttbr0(struct task_struct *tsk,
@@ -248,6 +254,9 @@
 void verify_cpu_asid_bits(void);
 void post_ttbr_update_workaround(void);
 
+unsigned long arm64_mm_context_get(struct mm_struct *mm);
+void arm64_mm_context_put(struct mm_struct *mm);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* !__ASM_MMU_CONTEXT_H */
diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
new file mode 100644
index 0000000..1c99fca
--- /dev/null
+++ b/arch/arm64/include/asm/mte.h
@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef __ASM_MTE_H
+#define __ASM_MTE_H
+
+#define MTE_GRANULE_SIZE	UL(16)
+#define MTE_GRANULE_MASK	(~(MTE_GRANULE_SIZE - 1))
+#define MTE_TAG_SHIFT		56
+#define MTE_TAG_SIZE		4
+
+#ifndef __ASSEMBLY__
+
+#include <linux/page-flags.h>
+
+#include <asm/pgtable-types.h>
+
+void mte_clear_page_tags(void *addr);
+unsigned long mte_copy_tags_from_user(void *to, const void __user *from,
+				      unsigned long n);
+unsigned long mte_copy_tags_to_user(void __user *to, void *from,
+				    unsigned long n);
+int mte_save_tags(struct page *page);
+void mte_save_page_tags(const void *page_addr, void *tag_storage);
+bool mte_restore_tags(swp_entry_t entry, struct page *page);
+void mte_restore_page_tags(void *page_addr, const void *tag_storage);
+void mte_invalidate_tags(int type, pgoff_t offset);
+void mte_invalidate_tags_area(int type);
+void *mte_allocate_tag_storage(void);
+void mte_free_tag_storage(char *storage);
+
+#ifdef CONFIG_ARM64_MTE
+
+/* track which pages have valid allocation tags */
+#define PG_mte_tagged	PG_arch_2
+
+void mte_sync_tags(pte_t *ptep, pte_t pte);
+void mte_copy_page_tags(void *kto, const void *kfrom);
+void flush_mte_state(void);
+void mte_thread_switch(struct task_struct *next);
+void mte_suspend_exit(void);
+long set_mte_ctrl(struct task_struct *task, unsigned long arg);
+long get_mte_ctrl(struct task_struct *task);
+int mte_ptrace_copy_tags(struct task_struct *child, long request,
+			 unsigned long addr, unsigned long data);
+
+#else
+
+/* unused if !CONFIG_ARM64_MTE, silence the compiler */
+#define PG_mte_tagged	0
+
+static inline void mte_sync_tags(pte_t *ptep, pte_t pte)
+{
+}
+static inline void mte_copy_page_tags(void *kto, const void *kfrom)
+{
+}
+static inline void flush_mte_state(void)
+{
+}
+static inline void mte_thread_switch(struct task_struct *next)
+{
+}
+static inline void mte_suspend_exit(void)
+{
+}
+static inline long set_mte_ctrl(struct task_struct *task, unsigned long arg)
+{
+	return 0;
+}
+static inline long get_mte_ctrl(struct task_struct *task)
+{
+	return 0;
+}
+static inline int mte_ptrace_copy_tags(struct task_struct *child,
+				       long request, unsigned long addr,
+				       unsigned long data)
+{
+	return -EIO;
+}
+
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_MTE_H  */
diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h
index 626ad01..dd87039 100644
--- a/arch/arm64/include/asm/numa.h
+++ b/arch/arm64/include/asm/numa.h
@@ -25,6 +25,9 @@
 /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
 static inline const struct cpumask *cpumask_of_node(int node)
 {
+	if (node == NUMA_NO_NODE)
+		return cpu_all_mask;
+
 	return node_to_cpumask_map[node];
 }
 #endif
diff --git a/arch/arm64/include/asm/page-def.h b/arch/arm64/include/asm/page-def.h
index f99d48e..2403f7b 100644
--- a/arch/arm64/include/asm/page-def.h
+++ b/arch/arm64/include/asm/page-def.h
@@ -11,13 +11,8 @@
 #include <linux/const.h>
 
 /* PAGE_SHIFT determines the page size */
-/* CONT_SHIFT determines the number of pages which can be tracked together  */
 #define PAGE_SHIFT		CONFIG_ARM64_PAGE_SHIFT
-#define CONT_SHIFT		CONFIG_ARM64_CONT_SHIFT
 #define PAGE_SIZE		(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK		(~(PAGE_SIZE-1))
 
-#define CONT_SIZE		(_AC(1, UL) << (CONT_SHIFT + PAGE_SHIFT))
-#define CONT_MASK		(~(CONT_SIZE-1))
-
 #endif /* __ASM_PAGE_DEF_H */
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index c01b52a..012cffc 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -15,18 +15,25 @@
 #include <linux/personality.h> /* for READ_IMPLIES_EXEC */
 #include <asm/pgtable-types.h>
 
-extern void __cpu_clear_user_page(void *p, unsigned long user);
-extern void __cpu_copy_user_page(void *to, const void *from,
-				 unsigned long user);
+struct page;
+struct vm_area_struct;
+
 extern void copy_page(void *to, const void *from);
 extern void clear_page(void *to);
 
+void copy_user_highpage(struct page *to, struct page *from,
+			unsigned long vaddr, struct vm_area_struct *vma);
+#define __HAVE_ARCH_COPY_USER_HIGHPAGE
+
+void copy_highpage(struct page *to, struct page *from);
+#define __HAVE_ARCH_COPY_HIGHPAGE
+
 #define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
 	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
-#define clear_user_page(addr,vaddr,pg)  __cpu_clear_user_page(addr, vaddr)
-#define copy_user_page(to,from,vaddr,pg) __cpu_copy_user_page(to, from, vaddr)
+#define clear_user_page(page, vaddr, pg)	clear_page(page)
+#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 
 typedef struct page *pgtable_t;
 
@@ -36,7 +43,7 @@
 
 #endif /* !__ASSEMBLY__ */
 
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
+#define VM_DATA_DEFAULT_FLAGS	(VM_DATA_FLAGS_TSK_EXEC | VM_MTE_ALLOWED)
 
 #include <asm-generic/getorder.h>
 
diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h
index 70b323c..b33ca26 100644
--- a/arch/arm64/include/asm/pci.h
+++ b/arch/arm64/include/asm/pci.h
@@ -17,6 +17,7 @@
 #define pcibios_assign_all_busses() \
 	(pci_has_flag(PCI_REASSIGN_ALL_BUS))
 
+#define arch_can_pci_mmap_wc() 1
 #define ARCH_GENERIC_PCI_MMAP_RESOURCE	1
 
 extern int isa_dma_bridge_buggy;
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 2c2d7db..60731f6 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -236,6 +236,9 @@
 #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
 
+/* PMMIR_EL1.SLOTS mask */
+#define ARMV8_PMU_SLOTS_MASK	0xff
+
 #ifdef CONFIG_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index d400a4d..94b3f2a 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -81,25 +81,15 @@
 /*
  * Contiguous page definitions.
  */
-#ifdef CONFIG_ARM64_64K_PAGES
-#define CONT_PTE_SHIFT		(5 + PAGE_SHIFT)
-#define CONT_PMD_SHIFT		(5 + PMD_SHIFT)
-#elif defined(CONFIG_ARM64_16K_PAGES)
-#define CONT_PTE_SHIFT		(7 + PAGE_SHIFT)
-#define CONT_PMD_SHIFT		(5 + PMD_SHIFT)
-#else
-#define CONT_PTE_SHIFT		(4 + PAGE_SHIFT)
-#define CONT_PMD_SHIFT		(4 + PMD_SHIFT)
-#endif
-
+#define CONT_PTE_SHIFT		(CONFIG_ARM64_CONT_PTE_SHIFT + PAGE_SHIFT)
 #define CONT_PTES		(1 << (CONT_PTE_SHIFT - PAGE_SHIFT))
 #define CONT_PTE_SIZE		(CONT_PTES * PAGE_SIZE)
 #define CONT_PTE_MASK		(~(CONT_PTE_SIZE - 1))
+
+#define CONT_PMD_SHIFT		(CONFIG_ARM64_CONT_PMD_SHIFT + PMD_SHIFT)
 #define CONT_PMDS		(1 << (CONT_PMD_SHIFT - PMD_SHIFT))
 #define CONT_PMD_SIZE		(CONT_PMDS * PMD_SIZE)
 #define CONT_PMD_MASK		(~(CONT_PMD_SIZE - 1))
-/* the numerical offset of the PTE within a range of CONT_PTES */
-#define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1))
 
 /*
  * Hardware page table definitions.
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 4d867c6..4cd0d6c 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -19,6 +19,13 @@
 #define PTE_DEVMAP		(_AT(pteval_t, 1) << 57)
 #define PTE_PROT_NONE		(_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */
 
+/*
+ * This bit indicates that the entry is present i.e. pmd_page()
+ * still points to a valid huge page in memory even if the pmd
+ * has been invalidated.
+ */
+#define PMD_PRESENT_INVALID	(_AT(pteval_t, 1) << 59) /* only when !PMD_SECT_VALID */
+
 #ifndef __ASSEMBLY__
 
 #include <asm/cpufeature.h>
@@ -50,6 +57,7 @@
 #define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
 #define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT))
 #define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
+#define PROT_NORMAL_TAGGED	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_TAGGED))
 
 #define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
@@ -59,6 +67,7 @@
 #define _HYP_PAGE_DEFAULT	_PAGE_DEFAULT
 
 #define PAGE_KERNEL		__pgprot(PROT_NORMAL)
+#define PAGE_KERNEL_TAGGED	__pgprot(PROT_NORMAL_TAGGED)
 #define PAGE_KERNEL_RO		__pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
 #define PAGE_KERNEL_ROX		__pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(PROT_NORMAL & ~PTE_PXN)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index d5d3fbe..a11bf52 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -9,6 +9,7 @@
 #include <asm/proc-fns.h>
 
 #include <asm/memory.h>
+#include <asm/mte.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable-prot.h>
 #include <asm/tlbflush.h>
@@ -35,11 +36,6 @@
 
 extern struct page *vmemmap;
 
-extern void __pte_error(const char *file, int line, unsigned long val);
-extern void __pmd_error(const char *file, int line, unsigned long val);
-extern void __pud_error(const char *file, int line, unsigned long val);
-extern void __pgd_error(const char *file, int line, unsigned long val);
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 
@@ -51,13 +47,22 @@
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /*
+ * Outside of a few very special situations (e.g. hibernation), we always
+ * use broadcast TLB invalidation instructions, therefore a spurious page
+ * fault on one CPU which has been handled concurrently by another CPU
+ * does not need to perform additional invalidation.
+ */
+#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0)
+
+/*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
  */
 extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define ZERO_PAGE(vaddr)	phys_to_page(__pa_symbol(empty_zero_page))
 
-#define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
+#define pte_ERROR(e)	\
+	pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e))
 
 /*
  * Macros to convert between a physical address and its placement in a
@@ -90,6 +95,8 @@
 #define pte_user_exec(pte)	(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
 #define pte_devmap(pte)		(!!(pte_val(pte) & PTE_DEVMAP))
+#define pte_tagged(pte)		((pte_val(pte) & PTE_ATTRINDX_MASK) == \
+				 PTE_ATTRINDX(MT_NORMAL_TAGGED))
 
 #define pte_cont_addr_end(addr, end)						\
 ({	unsigned long __boundary = ((addr) + CONT_PTE_SIZE) & CONT_PTE_MASK;	\
@@ -145,6 +152,18 @@
 	return pte;
 }
 
+static inline pmd_t clear_pmd_bit(pmd_t pmd, pgprot_t prot)
+{
+	pmd_val(pmd) &= ~pgprot_val(prot);
+	return pmd;
+}
+
+static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot)
+{
+	pmd_val(pmd) |= pgprot_val(prot);
+	return pmd;
+}
+
 static inline pte_t pte_wrprotect(pte_t pte)
 {
 	pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
@@ -284,6 +303,10 @@
 	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
 		__sync_icache_dcache(pte);
 
+	if (system_supports_mte() &&
+	    pte_present(pte) && pte_tagged(pte) && !pte_special(pte))
+		mte_sync_tags(ptep, pte);
+
 	__check_racy_pte_update(mm, ptep, pte);
 
 	set_pte(ptep, pte);
@@ -363,15 +386,24 @@
 }
 #endif
 
+#define pmd_present_invalid(pmd)     (!!(pmd_val(pmd) & PMD_PRESENT_INVALID))
+
+static inline int pmd_present(pmd_t pmd)
+{
+	return pte_present(pmd_pte(pmd)) || pmd_present_invalid(pmd);
+}
+
 /*
  * THP definitions.
  */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	return pmd_val(pmd) && pmd_present(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-#define pmd_present(pmd)	pte_present(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_valid(pmd)		pte_valid(pmd_pte(pmd))
@@ -381,7 +413,14 @@
 #define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
-#define pmd_mkinvalid(pmd)	(__pmd(pmd_val(pmd) & ~PMD_SECT_VALID))
+
+static inline pmd_t pmd_mkinvalid(pmd_t pmd)
+{
+	pmd = set_pmd_bit(pmd, __pgprot(PMD_PRESENT_INVALID));
+	pmd = clear_pmd_bit(pmd, __pgprot(PMD_SECT_VALID));
+
+	return pmd;
+}
 
 #define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
 
@@ -541,7 +580,8 @@
 
 #if CONFIG_PGTABLE_LEVELS > 2
 
-#define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd_val(pmd))
+#define pmd_ERROR(e)	\
+	pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e))
 
 #define pud_none(pud)		(!pud_val(pud))
 #define pud_bad(pud)		(!(pud_val(pud) & PUD_TABLE_BIT))
@@ -608,7 +648,8 @@
 
 #if CONFIG_PGTABLE_LEVELS > 3
 
-#define pud_ERROR(pud)		__pud_error(__FILE__, __LINE__, pud_val(pud))
+#define pud_ERROR(e)	\
+	pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e))
 
 #define p4d_none(p4d)		(!p4d_val(p4d))
 #define p4d_bad(p4d)		(!(p4d_val(p4d) & 2))
@@ -667,15 +708,21 @@
 
 #endif  /* CONFIG_PGTABLE_LEVELS > 3 */
 
-#define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))
+#define pgd_ERROR(e)	\
+	pr_err("%s:%d: bad pgd %016llx.\n", __FILE__, __LINE__, pgd_val(e))
 
 #define pgd_set_fixmap(addr)	((pgd_t *)set_fixmap_offset(FIX_PGD, addr))
 #define pgd_clear_fixmap()	clear_fixmap(FIX_PGD)
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
+	/*
+	 * Normal and Normal-Tagged are two different memory types and indices
+	 * in MAIR_EL1. The mask below has to include PTE_ATTRINDX_MASK.
+	 */
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
-			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP;
+			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP |
+			      PTE_ATTRINDX_MASK;
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
 		pte = pte_mkdirty(pte);
@@ -847,6 +894,11 @@
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(swp)	((pte_t) { (swp).val })
 
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+#define __pmd_to_swp_entry(pmd)		((swp_entry_t) { pmd_val(pmd) })
+#define __swp_entry_to_pmd(swp)		__pmd((swp).val)
+#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
+
 /*
  * Ensure that there are not more swap files than can be encoded in the kernel
  * PTEs.
@@ -855,6 +907,38 @@
 
 extern int kern_addr_valid(unsigned long addr);
 
+#ifdef CONFIG_ARM64_MTE
+
+#define __HAVE_ARCH_PREPARE_TO_SWAP
+static inline int arch_prepare_to_swap(struct page *page)
+{
+	if (system_supports_mte())
+		return mte_save_tags(page);
+	return 0;
+}
+
+#define __HAVE_ARCH_SWAP_INVALIDATE
+static inline void arch_swap_invalidate_page(int type, pgoff_t offset)
+{
+	if (system_supports_mte())
+		mte_invalidate_tags(type, offset);
+}
+
+static inline void arch_swap_invalidate_area(int type)
+{
+	if (system_supports_mte())
+		mte_invalidate_tags_area(type);
+}
+
+#define __HAVE_ARCH_SWAP_RESTORE
+static inline void arch_swap_restore(swp_entry_t entry, struct page *page)
+{
+	if (system_supports_mte() && mte_restore_tags(entry, page))
+		set_bit(PG_mte_tagged, &page->flags);
+}
+
+#endif /* CONFIG_ARM64_MTE */
+
 /*
  * On AArch64, the cache coherency is handled via the set_pte_at() function.
  */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 240fe5e..fce8cbe 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -38,6 +38,7 @@
 #include <asm/pgtable-hwdef.h>
 #include <asm/pointer_auth.h>
 #include <asm/ptrace.h>
+#include <asm/spectre.h>
 #include <asm/types.h>
 
 /*
@@ -151,6 +152,10 @@
 	struct ptrauth_keys_user	keys_user;
 	struct ptrauth_keys_kernel	keys_kernel;
 #endif
+#ifdef CONFIG_ARM64_MTE
+	u64			sctlr_tcf0;
+	u64			gcr_user_incl;
+#endif
 };
 
 static inline void arch_thread_struct_whitelist(unsigned long *offset,
@@ -197,40 +202,15 @@
 		regs->pmr_save = GIC_PRIO_IRQON;
 }
 
-static inline void set_ssbs_bit(struct pt_regs *regs)
-{
-	regs->pstate |= PSR_SSBS_BIT;
-}
-
-static inline void set_compat_ssbs_bit(struct pt_regs *regs)
-{
-	regs->pstate |= PSR_AA32_SSBS_BIT;
-}
-
 static inline void start_thread(struct pt_regs *regs, unsigned long pc,
 				unsigned long sp)
 {
 	start_thread_common(regs, pc);
 	regs->pstate = PSR_MODE_EL0t;
-
-	if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
-		set_ssbs_bit(regs);
-
+	spectre_v4_enable_task_mitigation(current);
 	regs->sp = sp;
 }
 
-static inline bool is_ttbr0_addr(unsigned long addr)
-{
-	/* entry assembly clears tags for TTBR0 addrs */
-	return addr < TASK_SIZE;
-}
-
-static inline bool is_ttbr1_addr(unsigned long addr)
-{
-	/* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */
-	return arch_kasan_reset_tag(addr) >= PAGE_OFFSET;
-}
-
 #ifdef CONFIG_COMPAT
 static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
 				       unsigned long sp)
@@ -244,13 +224,23 @@
 	regs->pstate |= PSR_AA32_E_BIT;
 #endif
 
-	if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
-		set_compat_ssbs_bit(regs);
-
+	spectre_v4_enable_task_mitigation(current);
 	regs->compat_sp = sp;
 }
 #endif
 
+static inline bool is_ttbr0_addr(unsigned long addr)
+{
+	/* entry assembly clears tags for TTBR0 addrs */
+	return addr < TASK_SIZE;
+}
+
+static inline bool is_ttbr1_addr(unsigned long addr)
+{
+	/* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */
+	return arch_kasan_reset_tag(addr) >= PAGE_OFFSET;
+}
+
 /* Forward declaration, a strange C thing */
 struct task_struct;
 
@@ -315,10 +305,10 @@
 
 #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
 /* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */
-long set_tagged_addr_ctrl(unsigned long arg);
-long get_tagged_addr_ctrl(void);
-#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(arg)
-#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl()
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg);
+long get_tagged_addr_ctrl(struct task_struct *task);
+#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(current, arg)
+#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl(current)
 #endif
 
 /*
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
new file mode 100644
index 0000000..fcdfbce
--- /dev/null
+++ b/arch/arm64/include/asm/spectre.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Interface for managing mitigations for Spectre vulnerabilities.
+ *
+ * Copyright (C) 2020 Google LLC
+ * Author: Will Deacon <will@kernel.org>
+ */
+
+#ifndef __ASM_SPECTRE_H
+#define __ASM_SPECTRE_H
+
+#include <asm/cpufeature.h>
+
+/* Watch out, ordering is important here. */
+enum mitigation_state {
+	SPECTRE_UNAFFECTED,
+	SPECTRE_MITIGATED,
+	SPECTRE_VULNERABLE,
+};
+
+struct task_struct;
+
+enum mitigation_state arm64_get_spectre_v2_state(void);
+bool has_spectre_v2(const struct arm64_cpu_capabilities *cap, int scope);
+void spectre_v2_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
+
+enum mitigation_state arm64_get_spectre_v4_state(void);
+bool has_spectre_v4(const struct arm64_cpu_capabilities *cap, int scope);
+void spectre_v4_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
+void spectre_v4_enable_task_mitigation(struct task_struct *tsk);
+
+#endif	/* __ASM_SPECTRE_H */
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index fc76130..eb29b1f 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -63,7 +63,7 @@
 
 extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame);
 extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
-			    int (*fn)(struct stackframe *, void *), void *data);
+			    bool (*fn)(void *, unsigned long), void *data);
 extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
 			   const char *loglvl);
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 554a7e8..d52c1b3 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -91,10 +91,12 @@
 #define PSTATE_PAN			pstate_field(0, 4)
 #define PSTATE_UAO			pstate_field(0, 3)
 #define PSTATE_SSBS			pstate_field(3, 1)
+#define PSTATE_TCO			pstate_field(3, 4)
 
 #define SET_PSTATE_PAN(x)		__emit_inst(0xd500401f | PSTATE_PAN | ((!!x) << PSTATE_Imm_shift))
 #define SET_PSTATE_UAO(x)		__emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift))
 #define SET_PSTATE_SSBS(x)		__emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_TCO(x)		__emit_inst(0xd500401f | PSTATE_TCO | ((!!x) << PSTATE_Imm_shift))
 
 #define __SYS_BARRIER_INSN(CRm, op2, Rt) \
 	__emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f))
@@ -181,6 +183,8 @@
 #define SYS_SCTLR_EL1			sys_reg(3, 0, 1, 0, 0)
 #define SYS_ACTLR_EL1			sys_reg(3, 0, 1, 0, 1)
 #define SYS_CPACR_EL1			sys_reg(3, 0, 1, 0, 2)
+#define SYS_RGSR_EL1			sys_reg(3, 0, 1, 0, 5)
+#define SYS_GCR_EL1			sys_reg(3, 0, 1, 0, 6)
 
 #define SYS_ZCR_EL1			sys_reg(3, 0, 1, 2, 0)
 
@@ -218,6 +222,8 @@
 #define SYS_ERXADDR_EL1			sys_reg(3, 0, 5, 4, 3)
 #define SYS_ERXMISC0_EL1		sys_reg(3, 0, 5, 5, 0)
 #define SYS_ERXMISC1_EL1		sys_reg(3, 0, 5, 5, 1)
+#define SYS_TFSR_EL1			sys_reg(3, 0, 5, 6, 0)
+#define SYS_TFSRE0_EL1			sys_reg(3, 0, 5, 6, 1)
 
 #define SYS_FAR_EL1			sys_reg(3, 0, 6, 0, 0)
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
@@ -321,6 +327,8 @@
 #define SYS_PMINTENSET_EL1		sys_reg(3, 0, 9, 14, 1)
 #define SYS_PMINTENCLR_EL1		sys_reg(3, 0, 9, 14, 2)
 
+#define SYS_PMMIR_EL1			sys_reg(3, 0, 9, 14, 6)
+
 #define SYS_MAIR_EL1			sys_reg(3, 0, 10, 2, 0)
 #define SYS_AMAIR_EL1			sys_reg(3, 0, 10, 3, 0)
 
@@ -368,6 +376,7 @@
 
 #define SYS_CCSIDR_EL1			sys_reg(3, 1, 0, 0, 0)
 #define SYS_CLIDR_EL1			sys_reg(3, 1, 0, 0, 1)
+#define SYS_GMID_EL1			sys_reg(3, 1, 0, 0, 4)
 #define SYS_AIDR_EL1			sys_reg(3, 1, 0, 0, 7)
 
 #define SYS_CSSELR_EL1			sys_reg(3, 2, 0, 0, 0)
@@ -460,6 +469,7 @@
 #define SYS_ESR_EL2			sys_reg(3, 4, 5, 2, 0)
 #define SYS_VSESR_EL2			sys_reg(3, 4, 5, 2, 3)
 #define SYS_FPEXC32_EL2			sys_reg(3, 4, 5, 3, 0)
+#define SYS_TFSR_EL2			sys_reg(3, 4, 5, 6, 0)
 #define SYS_FAR_EL2			sys_reg(3, 4, 6, 0, 0)
 
 #define SYS_VDISR_EL2			sys_reg(3, 4, 12, 1,  1)
@@ -516,6 +526,7 @@
 #define SYS_AFSR0_EL12			sys_reg(3, 5, 5, 1, 0)
 #define SYS_AFSR1_EL12			sys_reg(3, 5, 5, 1, 1)
 #define SYS_ESR_EL12			sys_reg(3, 5, 5, 2, 0)
+#define SYS_TFSR_EL12			sys_reg(3, 5, 5, 6, 0)
 #define SYS_FAR_EL12			sys_reg(3, 5, 6, 0, 0)
 #define SYS_MAIR_EL12			sys_reg(3, 5, 10, 2, 0)
 #define SYS_AMAIR_EL12			sys_reg(3, 5, 10, 3, 0)
@@ -531,6 +542,15 @@
 
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_DSSBS	(BIT(44))
+#define SCTLR_ELx_ATA	(BIT(43))
+
+#define SCTLR_ELx_TCF_SHIFT	40
+#define SCTLR_ELx_TCF_NONE	(UL(0x0) << SCTLR_ELx_TCF_SHIFT)
+#define SCTLR_ELx_TCF_SYNC	(UL(0x1) << SCTLR_ELx_TCF_SHIFT)
+#define SCTLR_ELx_TCF_ASYNC	(UL(0x2) << SCTLR_ELx_TCF_SHIFT)
+#define SCTLR_ELx_TCF_MASK	(UL(0x3) << SCTLR_ELx_TCF_SHIFT)
+
+#define SCTLR_ELx_ITFSB	(BIT(37))
 #define SCTLR_ELx_ENIA	(BIT(31))
 #define SCTLR_ELx_ENIB	(BIT(30))
 #define SCTLR_ELx_ENDA	(BIT(27))
@@ -559,6 +579,14 @@
 #endif
 
 /* SCTLR_EL1 specific flags. */
+#define SCTLR_EL1_ATA0		(BIT(42))
+
+#define SCTLR_EL1_TCF0_SHIFT	38
+#define SCTLR_EL1_TCF0_NONE	(UL(0x0) << SCTLR_EL1_TCF0_SHIFT)
+#define SCTLR_EL1_TCF0_SYNC	(UL(0x1) << SCTLR_EL1_TCF0_SHIFT)
+#define SCTLR_EL1_TCF0_ASYNC	(UL(0x2) << SCTLR_EL1_TCF0_SHIFT)
+#define SCTLR_EL1_TCF0_MASK	(UL(0x3) << SCTLR_EL1_TCF0_SHIFT)
+
 #define SCTLR_EL1_BT1		(BIT(36))
 #define SCTLR_EL1_BT0		(BIT(35))
 #define SCTLR_EL1_UCI		(BIT(26))
@@ -587,6 +615,7 @@
 			 SCTLR_EL1_SA0  | SCTLR_EL1_SED  | SCTLR_ELx_I    |\
 			 SCTLR_EL1_DZE  | SCTLR_EL1_UCT                   |\
 			 SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN |\
+			 SCTLR_ELx_ITFSB| SCTLR_ELx_ATA  | SCTLR_EL1_ATA0 |\
 			 ENDIAN_SET_EL1 | SCTLR_EL1_UCI  | SCTLR_EL1_RES1)
 
 /* MAIR_ELx memory attributes (used by Linux) */
@@ -595,6 +624,7 @@
 #define MAIR_ATTR_DEVICE_GRE		UL(0x0c)
 #define MAIR_ATTR_NORMAL_NC		UL(0x44)
 #define MAIR_ATTR_NORMAL_WT		UL(0xbb)
+#define MAIR_ATTR_NORMAL_TAGGED		UL(0xf0)
 #define MAIR_ATTR_NORMAL		UL(0xff)
 #define MAIR_ATTR_MASK			UL(0xff)
 
@@ -636,14 +666,22 @@
 #define ID_AA64ISAR1_APA_SHIFT		4
 #define ID_AA64ISAR1_DPB_SHIFT		0
 
-#define ID_AA64ISAR1_APA_NI		0x0
-#define ID_AA64ISAR1_APA_ARCHITECTED	0x1
-#define ID_AA64ISAR1_API_NI		0x0
-#define ID_AA64ISAR1_API_IMP_DEF	0x1
-#define ID_AA64ISAR1_GPA_NI		0x0
-#define ID_AA64ISAR1_GPA_ARCHITECTED	0x1
-#define ID_AA64ISAR1_GPI_NI		0x0
-#define ID_AA64ISAR1_GPI_IMP_DEF	0x1
+#define ID_AA64ISAR1_APA_NI			0x0
+#define ID_AA64ISAR1_APA_ARCHITECTED		0x1
+#define ID_AA64ISAR1_APA_ARCH_EPAC		0x2
+#define ID_AA64ISAR1_APA_ARCH_EPAC2		0x3
+#define ID_AA64ISAR1_APA_ARCH_EPAC2_FPAC	0x4
+#define ID_AA64ISAR1_APA_ARCH_EPAC2_FPAC_CMB	0x5
+#define ID_AA64ISAR1_API_NI			0x0
+#define ID_AA64ISAR1_API_IMP_DEF		0x1
+#define ID_AA64ISAR1_API_IMP_DEF_EPAC		0x2
+#define ID_AA64ISAR1_API_IMP_DEF_EPAC2		0x3
+#define ID_AA64ISAR1_API_IMP_DEF_EPAC2_FPAC	0x4
+#define ID_AA64ISAR1_API_IMP_DEF_EPAC2_FPAC_CMB	0x5
+#define ID_AA64ISAR1_GPA_NI			0x0
+#define ID_AA64ISAR1_GPA_ARCHITECTED		0x1
+#define ID_AA64ISAR1_GPI_NI			0x0
+#define ID_AA64ISAR1_GPI_IMP_DEF		0x1
 
 /* id_aa64pfr0 */
 #define ID_AA64PFR0_CSV3_SHIFT		60
@@ -686,6 +724,10 @@
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
 #define ID_AA64PFR1_BT_BTI		0x1
 
+#define ID_AA64PFR1_MTE_NI		0x0
+#define ID_AA64PFR1_MTE_EL0		0x1
+#define ID_AA64PFR1_MTE			0x2
+
 /* id_aa64zfr0 */
 #define ID_AA64ZFR0_F64MM_SHIFT		56
 #define ID_AA64ZFR0_F32MM_SHIFT		52
@@ -920,6 +962,28 @@
 #define CPACR_EL1_ZEN_EL0EN	(BIT(17)) /* enable EL0 access, if EL1EN set */
 #define CPACR_EL1_ZEN		(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)
 
+/* TCR EL1 Bit Definitions */
+#define SYS_TCR_EL1_TCMA1	(BIT(58))
+#define SYS_TCR_EL1_TCMA0	(BIT(57))
+
+/* GCR_EL1 Definitions */
+#define SYS_GCR_EL1_RRND	(BIT(16))
+#define SYS_GCR_EL1_EXCL_MASK	0xffffUL
+
+/* RGSR_EL1 Definitions */
+#define SYS_RGSR_EL1_TAG_MASK	0xfUL
+#define SYS_RGSR_EL1_SEED_SHIFT	8
+#define SYS_RGSR_EL1_SEED_MASK	0xffffUL
+
+/* GMID_EL1 field definitions */
+#define SYS_GMID_EL1_BS_SHIFT	0
+#define SYS_GMID_EL1_BS_SIZE	4
+
+/* TFSR{,E0}_EL1 bit definitions */
+#define SYS_TFSR_EL1_TF0_SHIFT	0
+#define SYS_TFSR_EL1_TF1_SHIFT	1
+#define SYS_TFSR_EL1_TF0	(UL(1) << SYS_TFSR_EL1_TF0_SHIFT)
+#define SYS_TFSR_EL1_TF1	(UK(2) << SYS_TFSR_EL1_TF1_SHIFT)
 
 /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */
 #define SYS_MPIDR_SAFE_VAL	(BIT(31))
@@ -1024,6 +1088,13 @@
 		write_sysreg(__scs_new, sysreg);			\
 } while (0)
 
+#define sysreg_clear_set_s(sysreg, clear, set) do {			\
+	u64 __scs_val = read_sysreg_s(sysreg);				\
+	u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set);		\
+	if (__scs_new != __scs_val)					\
+		write_sysreg_s(__scs_new, sysreg);			\
+} while (0)
+
 #endif
 
 #endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 5e784e1..1fbab85 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -67,6 +67,7 @@
 #define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
 #define TIF_UPROBE		4	/* uprobe breakpoint or singlestep */
 #define TIF_FSCHECK		5	/* Check FS is USER_DS on return */
+#define TIF_MTE_ASYNC_FAULT	6	/* MTE Asynchronous Tag Check Fault */
 #define TIF_SYSCALL_TRACE	8	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	9	/* syscall auditing */
 #define TIF_SYSCALL_TRACEPOINT	10	/* syscall tracepoint for ftrace */
@@ -96,10 +97,11 @@
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 #define _TIF_SVE		(1 << TIF_SVE)
+#define _TIF_MTE_ASYNC_FAULT	(1 << TIF_MTE_ASYNC_FAULT)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
 				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
-				 _TIF_UPROBE | _TIF_FSCHECK)
+				 _TIF_UPROBE | _TIF_FSCHECK | _TIF_MTE_ASYNC_FAULT)
 
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index d493174..cc3f5a3 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -28,14 +28,16 @@
  * not. The macros handles invoking the asm with or without the
  * register argument as appropriate.
  */
-#define __TLBI_0(op, arg) asm ("tlbi " #op "\n"				       \
+#define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE			       \
+			       "tlbi " #op "\n"				       \
 		   ALTERNATIVE("nop\n			nop",		       \
 			       "dsb ish\n		tlbi " #op,	       \
 			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
 			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
 			    : : )
 
-#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0\n"			       \
+#define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
+			       "tlbi " #op ", %0\n"			       \
 		   ALTERNATIVE("nop\n			nop",		       \
 			       "dsb ish\n		tlbi " #op ", %0",     \
 			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index cee5928..d96dc2c 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -24,7 +24,7 @@
 
 void register_undef_hook(struct undef_hook *hook);
 void unregister_undef_hook(struct undef_hook *hook);
-void force_signal_inject(int signal, int code, unsigned long address);
+void force_signal_inject(int signal, int code, unsigned long address, unsigned int err);
 void arm64_notify_segfault(unsigned long addr);
 void arm64_force_sig_fault(int signo, int code, void __user *addr, const char *str);
 void arm64_force_sig_mceerr(int code, void __user *addr, short lsb, const char *str);
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 912162f..b8f41aa 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -74,6 +74,6 @@
 #define HWCAP2_DGH		(1 << 15)
 #define HWCAP2_RNG		(1 << 16)
 #define HWCAP2_BTI		(1 << 17)
-/* reserved for HWCAP2_MTE	(1 << 18) */
+#define HWCAP2_MTE		(1 << 18)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index ba85bb2..7d804fd 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -242,6 +242,15 @@
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL		0
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL		1
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED	2
+
+/*
+ * Only two states can be presented by the host kernel:
+ * - NOT_REQUIRED: the guest doesn't need to do anything
+ * - NOT_AVAIL: the guest isn't mitigated (it can still use SSBS if available)
+ *
+ * All the other values are deprecated. The host still accepts all
+ * values (they are ABI), but will narrow them to the above two.
+ */
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2	KVM_REG_ARM_FW_REG(2)
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL		0
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN		1
diff --git a/arch/arm64/include/uapi/asm/mman.h b/arch/arm64/include/uapi/asm/mman.h
index 6fdd71e..1e6482a 100644
--- a/arch/arm64/include/uapi/asm/mman.h
+++ b/arch/arm64/include/uapi/asm/mman.h
@@ -5,5 +5,6 @@
 #include <asm-generic/mman.h>
 
 #define PROT_BTI	0x10		/* BTI guarded page */
+#define PROT_MTE	0x20		/* Normal Tagged mapping */
 
 #endif /* ! _UAPI__ASM_MMAN_H */
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 42cbe34..758ae98 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -51,6 +51,7 @@
 #define PSR_PAN_BIT	0x00400000
 #define PSR_UAO_BIT	0x00800000
 #define PSR_DIT_BIT	0x01000000
+#define PSR_TCO_BIT	0x02000000
 #define PSR_V_BIT	0x10000000
 #define PSR_C_BIT	0x20000000
 #define PSR_Z_BIT	0x40000000
@@ -75,6 +76,9 @@
 /* syscall emulation path in ptrace */
 #define PTRACE_SYSEMU		  31
 #define PTRACE_SYSEMU_SINGLESTEP  32
+/* MTE allocation tag access */
+#define PTRACE_PEEKMTETAGS	  33
+#define PTRACE_POKEMTETAGS	  34
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index a561cbb..bbaf0bc 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -3,8 +3,6 @@
 # Makefile for the linux kernel.
 #
 
-CPPFLAGS_vmlinux.lds	:= -DTEXT_OFFSET=$(TEXT_OFFSET)
-AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 CFLAGS_armv8_deprecated.o := -I$(src)
 
 CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
@@ -19,7 +17,7 @@
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
 			   smp.o smp_spin_table.o topology.o smccc-call.o	\
-			   syscall.o
+			   syscall.o proton-pack.o
 
 targets			+= efi-entry.o
 
@@ -59,9 +57,9 @@
 obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
 obj-$(CONFIG_CRASH_CORE)		+= crash_core.o
 obj-$(CONFIG_ARM_SDE_INTERFACE)		+= sdei.o
-obj-$(CONFIG_ARM64_SSBD)		+= ssbd.o
 obj-$(CONFIG_ARM64_PTR_AUTH)		+= pointer_auth.o
 obj-$(CONFIG_SHADOW_CALL_STACK)		+= scs.o
+obj-$(CONFIG_ARM64_MTE)			+= mte.o
 
 obj-y					+= vdso/ probes/
 obj-$(CONFIG_COMPAT_VDSO)		+= vdso32/
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 4559664..cada0b8 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -298,8 +298,21 @@
 		case EFI_BOOT_SERVICES_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
 		case EFI_PERSISTENT_MEMORY:
-			pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys);
-			return NULL;
+			if (memblock_is_map_memory(phys) ||
+			    !memblock_is_region_memory(phys, size)) {
+				pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys);
+				return NULL;
+			}
+			/*
+			 * Mapping kernel memory is permitted if the region in
+			 * question is covered by a single memblock with the
+			 * NOMAP attribute set: this enables the use of ACPI
+			 * table overrides passed via initramfs, which are
+			 * reserved in memory using arch_reserve_mem_area()
+			 * below. As this particular use case only requires
+			 * read access, fall through to the R/O mapping case.
+			 */
+			fallthrough;
 
 		case EFI_RUNTIME_SERVICES_CODE:
 			/*
@@ -322,7 +335,7 @@
 			 */
 			if (memblock_is_map_memory(phys))
 				return (void __iomem *)__phys_to_virt(phys);
-			/* fall through */
+			fallthrough;
 
 		default:
 			if (region->attribute & EFI_MEMORY_WB)
@@ -388,3 +401,8 @@
 
 	return err;
 }
+
+void arch_reserve_mem_area(acpi_physical_address addr, size_t size)
+{
+	memblock_mark_nomap(addr, size);
+}
diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S
index 4a18055..37721eb 100644
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -35,6 +35,10 @@
 	mov_q	x13, SCTLR_ELx_FLAGS
 	bic	x12, x12, x13
 	pre_disable_mmu_workaround
+	/*
+	 * either disable EL1&0 translation regime or disable EL2&0 translation
+	 * regime if HCR_EL2.E2H == 1
+	 */
 	msr	sctlr_el1, x12
 	isb
 
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 6bd1d3a..24d75af 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -106,365 +106,6 @@
 		sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
 }
 
-atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
-
-#include <asm/mmu_context.h>
-#include <asm/cacheflush.h>
-
-DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
-
-#ifdef CONFIG_KVM_INDIRECT_VECTORS
-static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
-				const char *hyp_vecs_end)
-{
-	void *dst = lm_alias(__bp_harden_hyp_vecs + slot * SZ_2K);
-	int i;
-
-	for (i = 0; i < SZ_2K; i += 0x80)
-		memcpy(dst + i, hyp_vecs_start, hyp_vecs_end - hyp_vecs_start);
-
-	__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
-}
-
-static void install_bp_hardening_cb(bp_hardening_cb_t fn,
-				    const char *hyp_vecs_start,
-				    const char *hyp_vecs_end)
-{
-	static DEFINE_RAW_SPINLOCK(bp_lock);
-	int cpu, slot = -1;
-
-	/*
-	 * detect_harden_bp_fw() passes NULL for the hyp_vecs start/end if
-	 * we're a guest. Skip the hyp-vectors work.
-	 */
-	if (!hyp_vecs_start) {
-		__this_cpu_write(bp_hardening_data.fn, fn);
-		return;
-	}
-
-	raw_spin_lock(&bp_lock);
-	for_each_possible_cpu(cpu) {
-		if (per_cpu(bp_hardening_data.fn, cpu) == fn) {
-			slot = per_cpu(bp_hardening_data.hyp_vectors_slot, cpu);
-			break;
-		}
-	}
-
-	if (slot == -1) {
-		slot = atomic_inc_return(&arm64_el2_vector_last_slot);
-		BUG_ON(slot >= BP_HARDEN_EL2_SLOTS);
-		__copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end);
-	}
-
-	__this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot);
-	__this_cpu_write(bp_hardening_data.fn, fn);
-	raw_spin_unlock(&bp_lock);
-}
-#else
-static void install_bp_hardening_cb(bp_hardening_cb_t fn,
-				      const char *hyp_vecs_start,
-				      const char *hyp_vecs_end)
-{
-	__this_cpu_write(bp_hardening_data.fn, fn);
-}
-#endif	/* CONFIG_KVM_INDIRECT_VECTORS */
-
-#include <linux/arm-smccc.h>
-
-static void __maybe_unused call_smc_arch_workaround_1(void)
-{
-	arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
-}
-
-static void call_hvc_arch_workaround_1(void)
-{
-	arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
-}
-
-static void qcom_link_stack_sanitization(void)
-{
-	u64 tmp;
-
-	asm volatile("mov	%0, x30		\n"
-		     ".rept	16		\n"
-		     "bl	. + 4		\n"
-		     ".endr			\n"
-		     "mov	x30, %0		\n"
-		     : "=&r" (tmp));
-}
-
-static bool __nospectre_v2;
-static int __init parse_nospectre_v2(char *str)
-{
-	__nospectre_v2 = true;
-	return 0;
-}
-early_param("nospectre_v2", parse_nospectre_v2);
-
-/*
- * -1: No workaround
- *  0: No workaround required
- *  1: Workaround installed
- */
-static int detect_harden_bp_fw(void)
-{
-	bp_hardening_cb_t cb;
-	void *smccc_start, *smccc_end;
-	struct arm_smccc_res res;
-	u32 midr = read_cpuid_id();
-
-	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-			     ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-
-	switch ((int)res.a0) {
-	case 1:
-		/* Firmware says we're just fine */
-		return 0;
-	case 0:
-		break;
-	default:
-		return -1;
-	}
-
-	switch (arm_smccc_1_1_get_conduit()) {
-	case SMCCC_CONDUIT_HVC:
-		cb = call_hvc_arch_workaround_1;
-		/* This is a guest, no need to patch KVM vectors */
-		smccc_start = NULL;
-		smccc_end = NULL;
-		break;
-
-#if IS_ENABLED(CONFIG_KVM)
-	case SMCCC_CONDUIT_SMC:
-		cb = call_smc_arch_workaround_1;
-		smccc_start = __smccc_workaround_1_smc;
-		smccc_end = __smccc_workaround_1_smc +
-			__SMCCC_WORKAROUND_1_SMC_SZ;
-		break;
-#endif
-
-	default:
-		return -1;
-	}
-
-	if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) ||
-	    ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1))
-		cb = qcom_link_stack_sanitization;
-
-	if (IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR))
-		install_bp_hardening_cb(cb, smccc_start, smccc_end);
-
-	return 1;
-}
-
-DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);
-
-int ssbd_state __read_mostly = ARM64_SSBD_KERNEL;
-static bool __ssb_safe = true;
-
-static const struct ssbd_options {
-	const char	*str;
-	int		state;
-} ssbd_options[] = {
-	{ "force-on",	ARM64_SSBD_FORCE_ENABLE, },
-	{ "force-off",	ARM64_SSBD_FORCE_DISABLE, },
-	{ "kernel",	ARM64_SSBD_KERNEL, },
-};
-
-static int __init ssbd_cfg(char *buf)
-{
-	int i;
-
-	if (!buf || !buf[0])
-		return -EINVAL;
-
-	for (i = 0; i < ARRAY_SIZE(ssbd_options); i++) {
-		int len = strlen(ssbd_options[i].str);
-
-		if (strncmp(buf, ssbd_options[i].str, len))
-			continue;
-
-		ssbd_state = ssbd_options[i].state;
-		return 0;
-	}
-
-	return -EINVAL;
-}
-early_param("ssbd", ssbd_cfg);
-
-void __init arm64_update_smccc_conduit(struct alt_instr *alt,
-				       __le32 *origptr, __le32 *updptr,
-				       int nr_inst)
-{
-	u32 insn;
-
-	BUG_ON(nr_inst != 1);
-
-	switch (arm_smccc_1_1_get_conduit()) {
-	case SMCCC_CONDUIT_HVC:
-		insn = aarch64_insn_get_hvc_value();
-		break;
-	case SMCCC_CONDUIT_SMC:
-		insn = aarch64_insn_get_smc_value();
-		break;
-	default:
-		return;
-	}
-
-	*updptr = cpu_to_le32(insn);
-}
-
-void __init arm64_enable_wa2_handling(struct alt_instr *alt,
-				      __le32 *origptr, __le32 *updptr,
-				      int nr_inst)
-{
-	BUG_ON(nr_inst != 1);
-	/*
-	 * Only allow mitigation on EL1 entry/exit and guest
-	 * ARCH_WORKAROUND_2 handling if the SSBD state allows it to
-	 * be flipped.
-	 */
-	if (arm64_get_ssbd_state() == ARM64_SSBD_KERNEL)
-		*updptr = cpu_to_le32(aarch64_insn_gen_nop());
-}
-
-void arm64_set_ssbd_mitigation(bool state)
-{
-	int conduit;
-
-	if (!IS_ENABLED(CONFIG_ARM64_SSBD)) {
-		pr_info_once("SSBD disabled by kernel configuration\n");
-		return;
-	}
-
-	if (this_cpu_has_cap(ARM64_SSBS)) {
-		if (state)
-			asm volatile(SET_PSTATE_SSBS(0));
-		else
-			asm volatile(SET_PSTATE_SSBS(1));
-		return;
-	}
-
-	conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, state,
-				       NULL);
-
-	WARN_ON_ONCE(conduit == SMCCC_CONDUIT_NONE);
-}
-
-static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
-				    int scope)
-{
-	struct arm_smccc_res res;
-	bool required = true;
-	s32 val;
-	bool this_cpu_safe = false;
-	int conduit;
-
-	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-
-	if (cpu_mitigations_off())
-		ssbd_state = ARM64_SSBD_FORCE_DISABLE;
-
-	/* delay setting __ssb_safe until we get a firmware response */
-	if (is_midr_in_range_list(read_cpuid_id(), entry->midr_range_list))
-		this_cpu_safe = true;
-
-	if (this_cpu_has_cap(ARM64_SSBS)) {
-		if (!this_cpu_safe)
-			__ssb_safe = false;
-		required = false;
-		goto out_printmsg;
-	}
-
-	conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				       ARM_SMCCC_ARCH_WORKAROUND_2, &res);
-
-	if (conduit == SMCCC_CONDUIT_NONE) {
-		ssbd_state = ARM64_SSBD_UNKNOWN;
-		if (!this_cpu_safe)
-			__ssb_safe = false;
-		return false;
-	}
-
-	val = (s32)res.a0;
-
-	switch (val) {
-	case SMCCC_RET_NOT_SUPPORTED:
-		ssbd_state = ARM64_SSBD_UNKNOWN;
-		if (!this_cpu_safe)
-			__ssb_safe = false;
-		return false;
-
-	/* machines with mixed mitigation requirements must not return this */
-	case SMCCC_RET_NOT_REQUIRED:
-		pr_info_once("%s mitigation not required\n", entry->desc);
-		ssbd_state = ARM64_SSBD_MITIGATED;
-		return false;
-
-	case SMCCC_RET_SUCCESS:
-		__ssb_safe = false;
-		required = true;
-		break;
-
-	case 1:	/* Mitigation not required on this CPU */
-		required = false;
-		break;
-
-	default:
-		WARN_ON(1);
-		if (!this_cpu_safe)
-			__ssb_safe = false;
-		return false;
-	}
-
-	switch (ssbd_state) {
-	case ARM64_SSBD_FORCE_DISABLE:
-		arm64_set_ssbd_mitigation(false);
-		required = false;
-		break;
-
-	case ARM64_SSBD_KERNEL:
-		if (required) {
-			__this_cpu_write(arm64_ssbd_callback_required, 1);
-			arm64_set_ssbd_mitigation(true);
-		}
-		break;
-
-	case ARM64_SSBD_FORCE_ENABLE:
-		arm64_set_ssbd_mitigation(true);
-		required = true;
-		break;
-
-	default:
-		WARN_ON(1);
-		break;
-	}
-
-out_printmsg:
-	switch (ssbd_state) {
-	case ARM64_SSBD_FORCE_DISABLE:
-		pr_info_once("%s disabled from command-line\n", entry->desc);
-		break;
-
-	case ARM64_SSBD_FORCE_ENABLE:
-		pr_info_once("%s forced from command-line\n", entry->desc);
-		break;
-	}
-
-	return required;
-}
-
-/* known invulnerable cores */
-static const struct midr_range arm64_ssb_cpus[] = {
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
-	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
-	{},
-};
-
 #ifdef CONFIG_ARM64_ERRATUM_1463225
 DEFINE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
 
@@ -519,83 +160,6 @@
 	.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,			\
 	CAP_MIDR_RANGE_LIST(midr_list)
 
-/* Track overall mitigation state. We are only mitigated if all cores are ok */
-static bool __hardenbp_enab = true;
-static bool __spectrev2_safe = true;
-
-int get_spectre_v2_workaround_state(void)
-{
-	if (__spectrev2_safe)
-		return ARM64_BP_HARDEN_NOT_REQUIRED;
-
-	if (!__hardenbp_enab)
-		return ARM64_BP_HARDEN_UNKNOWN;
-
-	return ARM64_BP_HARDEN_WA_NEEDED;
-}
-
-/*
- * List of CPUs that do not need any Spectre-v2 mitigation at all.
- */
-static const struct midr_range spectre_v2_safe_list[] = {
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
-	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
-	MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
-	{ /* sentinel */ }
-};
-
-/*
- * Track overall bp hardening for all heterogeneous cores in the machine.
- * We are only considered "safe" if all booted cores are known safe.
- */
-static bool __maybe_unused
-check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
-{
-	int need_wa;
-
-	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-
-	/* If the CPU has CSV2 set, we're safe */
-	if (cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64PFR0_EL1),
-						 ID_AA64PFR0_CSV2_SHIFT))
-		return false;
-
-	/* Alternatively, we have a list of unaffected CPUs */
-	if (is_midr_in_range_list(read_cpuid_id(), spectre_v2_safe_list))
-		return false;
-
-	/* Fallback to firmware detection */
-	need_wa = detect_harden_bp_fw();
-	if (!need_wa)
-		return false;
-
-	__spectrev2_safe = false;
-
-	if (!IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR)) {
-		pr_warn_once("spectrev2 mitigation disabled by kernel configuration\n");
-		__hardenbp_enab = false;
-		return false;
-	}
-
-	/* forced off */
-	if (__nospectre_v2 || cpu_mitigations_off()) {
-		pr_info_once("spectrev2 mitigation disabled by command line option\n");
-		__hardenbp_enab = false;
-		return false;
-	}
-
-	if (need_wa < 0) {
-		pr_warn_once("ARM_SMCCC_ARCH_WORKAROUND_1 missing from firmware\n");
-		__hardenbp_enab = false;
-	}
-
-	return (need_wa > 0);
-}
-
 static const __maybe_unused struct midr_range tx2_family_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
 	MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
@@ -887,9 +451,11 @@
 	},
 #endif
 	{
-		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		.desc = "Spectre-v2",
+		.capability = ARM64_SPECTRE_V2,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
-		.matches = check_branch_predictor,
+		.matches = has_spectre_v2,
+		.cpu_enable = spectre_v2_enable_mitigation,
 	},
 #ifdef CONFIG_RANDOMIZE_BASE
 	{
@@ -899,17 +465,23 @@
 	},
 #endif
 	{
-		.desc = "Speculative Store Bypass Disable",
-		.capability = ARM64_SSBD,
+		.desc = "Spectre-v4",
+		.capability = ARM64_SPECTRE_V4,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
-		.matches = has_ssbd_mitigation,
-		.midr_range_list = arm64_ssb_cpus,
+		.matches = has_spectre_v4,
+		.cpu_enable = spectre_v4_enable_mitigation,
 	},
 #ifdef CONFIG_ARM64_ERRATUM_1418040
 	{
 		.desc = "ARM erratum 1418040",
 		.capability = ARM64_WORKAROUND_1418040,
 		ERRATA_MIDR_RANGE_LIST(erratum_1418040_list),
+		/*
+		 * We need to allow affected CPUs to come in late, but
+		 * also need the non-affected CPUs to be able to come
+		 * in at any point in time. Wonderful.
+		 */
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
 	},
 #endif
 #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT
@@ -954,40 +526,3 @@
 	{
 	}
 };
-
-ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr,
-			    char *buf)
-{
-	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
-}
-
-ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
-		char *buf)
-{
-	switch (get_spectre_v2_workaround_state()) {
-	case ARM64_BP_HARDEN_NOT_REQUIRED:
-		return sprintf(buf, "Not affected\n");
-        case ARM64_BP_HARDEN_WA_NEEDED:
-		return sprintf(buf, "Mitigation: Branch predictor hardening\n");
-        case ARM64_BP_HARDEN_UNKNOWN:
-	default:
-		return sprintf(buf, "Vulnerable\n");
-	}
-}
-
-ssize_t cpu_show_spec_store_bypass(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	if (__ssb_safe)
-		return sprintf(buf, "Not affected\n");
-
-	switch (ssbd_state) {
-	case ARM64_SSBD_KERNEL:
-	case ARM64_SSBD_FORCE_ENABLE:
-		if (IS_ENABLED(CONFIG_ARM64_SSBD))
-			return sprintf(buf,
-			    "Mitigation: Speculative Store Bypass disabled via prctl\n");
-	}
-
-	return sprintf(buf, "Vulnerable\n");
-}
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index a389b99..dcc165b 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -75,6 +75,7 @@
 #include <asm/cpu_ops.h>
 #include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
+#include <asm/mte.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
 #include <asm/traps.h>
@@ -197,9 +198,9 @@
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FCMA_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_JSCVT_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
-		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_API_SHIFT, 4, 0),
+		       FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_API_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
-		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_APA_SHIFT, 4, 0),
+		       FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_APA_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_DPB_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
@@ -227,7 +228,9 @@
 static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MPAMFRAC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_RASFRAC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_MTE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MTE_SHIFT, 4, ID_AA64PFR1_MTE_NI),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_BTI),
 				    FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_BT_SHIFT, 4, 0),
 	ARM64_FTR_END,
@@ -487,7 +490,7 @@
 };
 
 static const struct arm64_ftr_bits ftr_id_pfr2[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR2_SSBS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_SSBS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_CSV3_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
@@ -686,7 +689,7 @@
 	case FTR_HIGHER_OR_ZERO_SAFE:
 		if (!cur || !new)
 			break;
-		/* Fallthrough */
+		fallthrough;
 	case FTR_HIGHER_SAFE:
 		ret = new > cur ? new : cur;
 		break;
@@ -1111,6 +1114,7 @@
 		return 0;
 	return regp->sys_val;
 }
+EXPORT_SYMBOL_GPL(read_sanitised_ftr_reg);
 
 #define read_sysreg_case(r)	\
 	case r:		return read_sysreg_s(r)
@@ -1443,6 +1447,7 @@
 
 	write_sysreg(tcr, tcr_el1);
 	isb();
+	local_flush_tlb_all();
 }
 
 static bool cpu_has_broken_dbm(void)
@@ -1583,48 +1588,6 @@
 	WARN_ON(val & (7 << 27 | 7 << 21));
 }
 
-#ifdef CONFIG_ARM64_SSBD
-static int ssbs_emulation_handler(struct pt_regs *regs, u32 instr)
-{
-	if (user_mode(regs))
-		return 1;
-
-	if (instr & BIT(PSTATE_Imm_shift))
-		regs->pstate |= PSR_SSBS_BIT;
-	else
-		regs->pstate &= ~PSR_SSBS_BIT;
-
-	arm64_skip_faulting_instruction(regs, 4);
-	return 0;
-}
-
-static struct undef_hook ssbs_emulation_hook = {
-	.instr_mask	= ~(1U << PSTATE_Imm_shift),
-	.instr_val	= 0xd500401f | PSTATE_SSBS,
-	.fn		= ssbs_emulation_handler,
-};
-
-static void cpu_enable_ssbs(const struct arm64_cpu_capabilities *__unused)
-{
-	static bool undef_hook_registered = false;
-	static DEFINE_RAW_SPINLOCK(hook_lock);
-
-	raw_spin_lock(&hook_lock);
-	if (!undef_hook_registered) {
-		register_undef_hook(&ssbs_emulation_hook);
-		undef_hook_registered = true;
-	}
-	raw_spin_unlock(&hook_lock);
-
-	if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
-		sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS);
-		arm64_set_ssbd_mitigation(false);
-	} else {
-		arm64_set_ssbd_mitigation(true);
-	}
-}
-#endif /* CONFIG_ARM64_SSBD */
-
 #ifdef CONFIG_ARM64_PAN
 static void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
 {
@@ -1648,11 +1611,37 @@
 #endif /* CONFIG_ARM64_RAS_EXTN */
 
 #ifdef CONFIG_ARM64_PTR_AUTH
-static bool has_address_auth(const struct arm64_cpu_capabilities *entry,
-			     int __unused)
+static bool has_address_auth_cpucap(const struct arm64_cpu_capabilities *entry, int scope)
 {
-	return __system_matches_cap(ARM64_HAS_ADDRESS_AUTH_ARCH) ||
-	       __system_matches_cap(ARM64_HAS_ADDRESS_AUTH_IMP_DEF);
+	int boot_val, sec_val;
+
+	/* We don't expect to be called with SCOPE_SYSTEM */
+	WARN_ON(scope == SCOPE_SYSTEM);
+	/*
+	 * The ptr-auth feature levels are not intercompatible with lower
+	 * levels. Hence we must match ptr-auth feature level of the secondary
+	 * CPUs with that of the boot CPU. The level of boot cpu is fetched
+	 * from the sanitised register whereas direct register read is done for
+	 * the secondary CPUs.
+	 * The sanitised feature state is guaranteed to match that of the
+	 * boot CPU as a mismatched secondary CPU is parked before it gets
+	 * a chance to update the state, with the capability.
+	 */
+	boot_val = cpuid_feature_extract_field(read_sanitised_ftr_reg(entry->sys_reg),
+					       entry->field_pos, entry->sign);
+	if (scope & SCOPE_BOOT_CPU)
+		return boot_val >= entry->min_field_value;
+	/* Now check for the secondary CPUs with SCOPE_LOCAL_CPU scope */
+	sec_val = cpuid_feature_extract_field(__read_sysreg_by_encoding(entry->sys_reg),
+					      entry->field_pos, entry->sign);
+	return sec_val == boot_val;
+}
+
+static bool has_address_auth_metacap(const struct arm64_cpu_capabilities *entry,
+				     int scope)
+{
+	return has_address_auth_cpucap(cpu_hwcaps_ptrs[ARM64_HAS_ADDRESS_AUTH_ARCH], scope) ||
+	       has_address_auth_cpucap(cpu_hwcaps_ptrs[ARM64_HAS_ADDRESS_AUTH_IMP_DEF], scope);
 }
 
 static bool has_generic_auth(const struct arm64_cpu_capabilities *entry,
@@ -1702,6 +1691,22 @@
 }
 #endif /* CONFIG_ARM64_BTI */
 
+#ifdef CONFIG_ARM64_MTE
+static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap)
+{
+	static bool cleared_zero_page = false;
+
+	/*
+	 * Clear the tags in the zero page. This needs to be done via the
+	 * linear map which has the Tagged attribute.
+	 */
+	if (!cleared_zero_page) {
+		cleared_zero_page = true;
+		mte_clear_page_tags(lm_alias(empty_zero_page));
+	}
+}
+#endif /* CONFIG_ARM64_MTE */
+
 /* Internal helper functions to match cpu capability type */
 static bool
 cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
@@ -1976,19 +1981,16 @@
 		.field_pos = ID_AA64ISAR0_CRC32_SHIFT,
 		.min_field_value = 1,
 	},
-#ifdef CONFIG_ARM64_SSBD
 	{
 		.desc = "Speculative Store Bypassing Safe (SSBS)",
 		.capability = ARM64_SSBS,
-		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64PFR1_EL1,
 		.field_pos = ID_AA64PFR1_SSBS_SHIFT,
 		.sign = FTR_UNSIGNED,
 		.min_field_value = ID_AA64PFR1_SSBS_PSTATE_ONLY,
-		.cpu_enable = cpu_enable_ssbs,
 	},
-#endif
 #ifdef CONFIG_ARM64_CNP
 	{
 		.desc = "Common not Private translations",
@@ -2021,7 +2023,7 @@
 		.sign = FTR_UNSIGNED,
 		.field_pos = ID_AA64ISAR1_APA_SHIFT,
 		.min_field_value = ID_AA64ISAR1_APA_ARCHITECTED,
-		.matches = has_cpuid_feature,
+		.matches = has_address_auth_cpucap,
 	},
 	{
 		.desc = "Address authentication (IMP DEF algorithm)",
@@ -2031,12 +2033,12 @@
 		.sign = FTR_UNSIGNED,
 		.field_pos = ID_AA64ISAR1_API_SHIFT,
 		.min_field_value = ID_AA64ISAR1_API_IMP_DEF,
-		.matches = has_cpuid_feature,
+		.matches = has_address_auth_cpucap,
 	},
 	{
 		.capability = ARM64_HAS_ADDRESS_AUTH,
 		.type = ARM64_CPUCAP_BOOT_CPU_FEATURE,
-		.matches = has_address_auth,
+		.matches = has_address_auth_metacap,
 	},
 	{
 		.desc = "Generic authentication (architected algorithm)",
@@ -2121,6 +2123,19 @@
 		.sign = FTR_UNSIGNED,
 	},
 #endif
+#ifdef CONFIG_ARM64_MTE
+	{
+		.desc = "Memory Tagging Extension",
+		.capability = ARM64_MTE,
+		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64PFR1_EL1,
+		.field_pos = ID_AA64PFR1_MTE_SHIFT,
+		.min_field_value = ID_AA64PFR1_MTE,
+		.sign = FTR_UNSIGNED,
+		.cpu_enable = cpu_enable_mte,
+	},
+#endif /* CONFIG_ARM64_MTE */
 	{},
 };
 
@@ -2237,6 +2252,9 @@
 	HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA),
 	HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG),
 #endif
+#ifdef CONFIG_ARM64_MTE
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_MTE_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_MTE, CAP_HWCAP, KERNEL_HWCAP_MTE),
+#endif /* CONFIG_ARM64_MTE */
 	{},
 };
 
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 393c6fb..6a7bb372 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -43,94 +43,93 @@
 unsigned long __icache_flags;
 
 static const char *const hwcap_str[] = {
-	"fp",
-	"asimd",
-	"evtstrm",
-	"aes",
-	"pmull",
-	"sha1",
-	"sha2",
-	"crc32",
-	"atomics",
-	"fphp",
-	"asimdhp",
-	"cpuid",
-	"asimdrdm",
-	"jscvt",
-	"fcma",
-	"lrcpc",
-	"dcpop",
-	"sha3",
-	"sm3",
-	"sm4",
-	"asimddp",
-	"sha512",
-	"sve",
-	"asimdfhm",
-	"dit",
-	"uscat",
-	"ilrcpc",
-	"flagm",
-	"ssbs",
-	"sb",
-	"paca",
-	"pacg",
-	"dcpodp",
-	"sve2",
-	"sveaes",
-	"svepmull",
-	"svebitperm",
-	"svesha3",
-	"svesm4",
-	"flagm2",
-	"frint",
-	"svei8mm",
-	"svef32mm",
-	"svef64mm",
-	"svebf16",
-	"i8mm",
-	"bf16",
-	"dgh",
-	"rng",
-	"bti",
-	/* reserved for "mte" */
-	NULL
+	[KERNEL_HWCAP_FP]		= "fp",
+	[KERNEL_HWCAP_ASIMD]		= "asimd",
+	[KERNEL_HWCAP_EVTSTRM]		= "evtstrm",
+	[KERNEL_HWCAP_AES]		= "aes",
+	[KERNEL_HWCAP_PMULL]		= "pmull",
+	[KERNEL_HWCAP_SHA1]		= "sha1",
+	[KERNEL_HWCAP_SHA2]		= "sha2",
+	[KERNEL_HWCAP_CRC32]		= "crc32",
+	[KERNEL_HWCAP_ATOMICS]		= "atomics",
+	[KERNEL_HWCAP_FPHP]		= "fphp",
+	[KERNEL_HWCAP_ASIMDHP]		= "asimdhp",
+	[KERNEL_HWCAP_CPUID]		= "cpuid",
+	[KERNEL_HWCAP_ASIMDRDM]		= "asimdrdm",
+	[KERNEL_HWCAP_JSCVT]		= "jscvt",
+	[KERNEL_HWCAP_FCMA]		= "fcma",
+	[KERNEL_HWCAP_LRCPC]		= "lrcpc",
+	[KERNEL_HWCAP_DCPOP]		= "dcpop",
+	[KERNEL_HWCAP_SHA3]		= "sha3",
+	[KERNEL_HWCAP_SM3]		= "sm3",
+	[KERNEL_HWCAP_SM4]		= "sm4",
+	[KERNEL_HWCAP_ASIMDDP]		= "asimddp",
+	[KERNEL_HWCAP_SHA512]		= "sha512",
+	[KERNEL_HWCAP_SVE]		= "sve",
+	[KERNEL_HWCAP_ASIMDFHM]		= "asimdfhm",
+	[KERNEL_HWCAP_DIT]		= "dit",
+	[KERNEL_HWCAP_USCAT]		= "uscat",
+	[KERNEL_HWCAP_ILRCPC]		= "ilrcpc",
+	[KERNEL_HWCAP_FLAGM]		= "flagm",
+	[KERNEL_HWCAP_SSBS]		= "ssbs",
+	[KERNEL_HWCAP_SB]		= "sb",
+	[KERNEL_HWCAP_PACA]		= "paca",
+	[KERNEL_HWCAP_PACG]		= "pacg",
+	[KERNEL_HWCAP_DCPODP]		= "dcpodp",
+	[KERNEL_HWCAP_SVE2]		= "sve2",
+	[KERNEL_HWCAP_SVEAES]		= "sveaes",
+	[KERNEL_HWCAP_SVEPMULL]		= "svepmull",
+	[KERNEL_HWCAP_SVEBITPERM]	= "svebitperm",
+	[KERNEL_HWCAP_SVESHA3]		= "svesha3",
+	[KERNEL_HWCAP_SVESM4]		= "svesm4",
+	[KERNEL_HWCAP_FLAGM2]		= "flagm2",
+	[KERNEL_HWCAP_FRINT]		= "frint",
+	[KERNEL_HWCAP_SVEI8MM]		= "svei8mm",
+	[KERNEL_HWCAP_SVEF32MM]		= "svef32mm",
+	[KERNEL_HWCAP_SVEF64MM]		= "svef64mm",
+	[KERNEL_HWCAP_SVEBF16]		= "svebf16",
+	[KERNEL_HWCAP_I8MM]		= "i8mm",
+	[KERNEL_HWCAP_BF16]		= "bf16",
+	[KERNEL_HWCAP_DGH]		= "dgh",
+	[KERNEL_HWCAP_RNG]		= "rng",
+	[KERNEL_HWCAP_BTI]		= "bti",
+	[KERNEL_HWCAP_MTE]		= "mte",
 };
 
 #ifdef CONFIG_COMPAT
+#define COMPAT_KERNEL_HWCAP(x)	const_ilog2(COMPAT_HWCAP_ ## x)
 static const char *const compat_hwcap_str[] = {
-	"swp",
-	"half",
-	"thumb",
-	"26bit",
-	"fastmult",
-	"fpa",
-	"vfp",
-	"edsp",
-	"java",
-	"iwmmxt",
-	"crunch",
-	"thumbee",
-	"neon",
-	"vfpv3",
-	"vfpv3d16",
-	"tls",
-	"vfpv4",
-	"idiva",
-	"idivt",
-	"vfpd32",
-	"lpae",
-	"evtstrm",
-	NULL
+	[COMPAT_KERNEL_HWCAP(SWP)]	= "swp",
+	[COMPAT_KERNEL_HWCAP(HALF)]	= "half",
+	[COMPAT_KERNEL_HWCAP(THUMB)]	= "thumb",
+	[COMPAT_KERNEL_HWCAP(26BIT)]	= NULL,	/* Not possible on arm64 */
+	[COMPAT_KERNEL_HWCAP(FAST_MULT)] = "fastmult",
+	[COMPAT_KERNEL_HWCAP(FPA)]	= NULL,	/* Not possible on arm64 */
+	[COMPAT_KERNEL_HWCAP(VFP)]	= "vfp",
+	[COMPAT_KERNEL_HWCAP(EDSP)]	= "edsp",
+	[COMPAT_KERNEL_HWCAP(JAVA)]	= NULL,	/* Not possible on arm64 */
+	[COMPAT_KERNEL_HWCAP(IWMMXT)]	= NULL,	/* Not possible on arm64 */
+	[COMPAT_KERNEL_HWCAP(CRUNCH)]	= NULL,	/* Not possible on arm64 */
+	[COMPAT_KERNEL_HWCAP(THUMBEE)]	= NULL,	/* Not possible on arm64 */
+	[COMPAT_KERNEL_HWCAP(NEON)]	= "neon",
+	[COMPAT_KERNEL_HWCAP(VFPv3)]	= "vfpv3",
+	[COMPAT_KERNEL_HWCAP(VFPV3D16)]	= NULL,	/* Not possible on arm64 */
+	[COMPAT_KERNEL_HWCAP(TLS)]	= "tls",
+	[COMPAT_KERNEL_HWCAP(VFPv4)]	= "vfpv4",
+	[COMPAT_KERNEL_HWCAP(IDIVA)]	= "idiva",
+	[COMPAT_KERNEL_HWCAP(IDIVT)]	= "idivt",
+	[COMPAT_KERNEL_HWCAP(VFPD32)]	= NULL,	/* Not possible on arm64 */
+	[COMPAT_KERNEL_HWCAP(LPAE)]	= "lpae",
+	[COMPAT_KERNEL_HWCAP(EVTSTRM)]	= "evtstrm",
 };
 
+#define COMPAT_KERNEL_HWCAP2(x)	const_ilog2(COMPAT_HWCAP2_ ## x)
 static const char *const compat_hwcap2_str[] = {
-	"aes",
-	"pmull",
-	"sha1",
-	"sha2",
-	"crc32",
-	NULL
+	[COMPAT_KERNEL_HWCAP2(AES)]	= "aes",
+	[COMPAT_KERNEL_HWCAP2(PMULL)]	= "pmull",
+	[COMPAT_KERNEL_HWCAP2(SHA1)]	= "sha1",
+	[COMPAT_KERNEL_HWCAP2(SHA2)]	= "sha2",
+	[COMPAT_KERNEL_HWCAP2(CRC32)]	= "crc32",
 };
 #endif /* CONFIG_COMPAT */
 
@@ -166,16 +165,25 @@
 		seq_puts(m, "Features\t:");
 		if (compat) {
 #ifdef CONFIG_COMPAT
-			for (j = 0; compat_hwcap_str[j]; j++)
-				if (compat_elf_hwcap & (1 << j))
-					seq_printf(m, " %s", compat_hwcap_str[j]);
+			for (j = 0; j < ARRAY_SIZE(compat_hwcap_str); j++) {
+				if (compat_elf_hwcap & (1 << j)) {
+					/*
+					 * Warn once if any feature should not
+					 * have been present on arm64 platform.
+					 */
+					if (WARN_ON_ONCE(!compat_hwcap_str[j]))
+						continue;
 
-			for (j = 0; compat_hwcap2_str[j]; j++)
+					seq_printf(m, " %s", compat_hwcap_str[j]);
+				}
+			}
+
+			for (j = 0; j < ARRAY_SIZE(compat_hwcap2_str); j++)
 				if (compat_elf_hwcap2 & (1 << j))
 					seq_printf(m, " %s", compat_hwcap2_str[j]);
 #endif /* CONFIG_COMPAT */
 		} else {
-			for (j = 0; hwcap_str[j]; j++)
+			for (j = 0; j < ARRAY_SIZE(hwcap_str); j++)
 				if (cpu_have_feature(j))
 					seq_printf(m, " %s", hwcap_str[j]);
 		}
@@ -327,7 +335,6 @@
 		set_bit(ICACHEF_VPIPT, &__icache_flags);
 		break;
 	default:
-		/* Fallthrough */
 	case ICACHE_POLICY_VIPT:
 		/* Assume aliasing */
 		set_bit(ICACHEF_ALIASING, &__icache_flags);
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 7310a4f..fa76151 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -384,7 +384,7 @@
 	hook_debug_fault_code(DBG_ESR_EVT_HWSS, single_step_handler, SIGTRAP,
 			      TRAP_TRACE, "single-step handler");
 	hook_debug_fault_code(DBG_ESR_EVT_BRK, brk_handler, SIGTRAP,
-			      TRAP_BRKPT, "ptrace BRK handler");
+			      TRAP_BRKPT, "BRK handler");
 }
 
 /* Re-enable single step for syscall restarting. */
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index d3be9db..43d4c32 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -66,6 +66,13 @@
 }
 NOKPROBE_SYMBOL(el1_dbg);
 
+static void notrace el1_fpac(struct pt_regs *regs, unsigned long esr)
+{
+	local_daif_inherit(regs);
+	do_ptrauth_fault(regs, esr);
+}
+NOKPROBE_SYMBOL(el1_fpac);
+
 asmlinkage void notrace el1_sync_handler(struct pt_regs *regs)
 {
 	unsigned long esr = read_sysreg(esr_el1);
@@ -92,6 +99,9 @@
 	case ESR_ELx_EC_BRK64:
 		el1_dbg(regs, esr);
 		break;
+	case ESR_ELx_EC_FPAC:
+		el1_fpac(regs, esr);
+		break;
 	default:
 		el1_inv(regs, esr);
 	}
@@ -227,6 +237,14 @@
 }
 NOKPROBE_SYMBOL(el0_svc);
 
+static void notrace el0_fpac(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_ptrauth_fault(regs, esr);
+}
+NOKPROBE_SYMBOL(el0_fpac);
+
 asmlinkage void notrace el0_sync_handler(struct pt_regs *regs)
 {
 	unsigned long esr = read_sysreg(esr_el1);
@@ -272,6 +290,9 @@
 	case ESR_ELx_EC_BRK64:
 		el0_dbg(regs, esr);
 		break;
+	case ESR_ELx_EC_FPAC:
+		el0_fpac(regs, esr);
+		break;
 	default:
 		el0_inv(regs, esr);
 	}
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index f880dd6..2ca395c 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -32,6 +32,7 @@
 SYM_FUNC_END(fpsimd_load_state)
 
 #ifdef CONFIG_ARM64_SVE
+
 SYM_FUNC_START(sve_save_state)
 	sve_save 0, x1, 2
 	ret
@@ -46,4 +47,28 @@
 	_sve_rdvl	0, 1
 	ret
 SYM_FUNC_END(sve_get_vl)
+
+/*
+ * Load SVE state from FPSIMD state.
+ *
+ * x0 = pointer to struct fpsimd_state
+ * x1 = VQ - 1
+ *
+ * Each SVE vector will be loaded with the first 128-bits taken from FPSIMD
+ * and the rest zeroed. All the other SVE registers will be zeroed.
+ */
+SYM_FUNC_START(sve_load_from_fpsimd_state)
+		sve_load_vq	x1, x2, x3
+		fpsimd_restore	x0, 8
+ _for n, 0, 15, _sve_pfalse	\n
+		_sve_wrffr	0
+		ret
+SYM_FUNC_END(sve_load_from_fpsimd_state)
+
+/* Zero all SVE registers but the first 128-bits of each vector */
+SYM_FUNC_START(sve_flush_live)
+	sve_flush
+	ret
+SYM_FUNC_END(sve_flush_live)
+
 #endif /* CONFIG_ARM64_SVE */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 2646178..f30007d 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -132,9 +132,8 @@
 	 * them if required.
 	 */
 	.macro	apply_ssbd, state, tmp1, tmp2
-#ifdef CONFIG_ARM64_SSBD
-alternative_cb	arm64_enable_wa2_handling
-	b	.L__asm_ssbd_skip\@
+alternative_cb	spectre_v4_patch_fw_mitigation_enable
+	b	.L__asm_ssbd_skip\@		// Patched to NOP
 alternative_cb_end
 	ldr_this_cpu	\tmp2, arm64_ssbd_callback_required, \tmp1
 	cbz	\tmp2,	.L__asm_ssbd_skip\@
@@ -142,10 +141,35 @@
 	tbnz	\tmp2, #TIF_SSBD, .L__asm_ssbd_skip\@
 	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_2
 	mov	w1, #\state
-alternative_cb	arm64_update_smccc_conduit
+alternative_cb	spectre_v4_patch_fw_mitigation_conduit
 	nop					// Patched to SMC/HVC #0
 alternative_cb_end
 .L__asm_ssbd_skip\@:
+	.endm
+
+	/* Check for MTE asynchronous tag check faults */
+	.macro check_mte_async_tcf, flgs, tmp
+#ifdef CONFIG_ARM64_MTE
+alternative_if_not ARM64_MTE
+	b	1f
+alternative_else_nop_endif
+	mrs_s	\tmp, SYS_TFSRE0_EL1
+	tbz	\tmp, #SYS_TFSR_EL1_TF0_SHIFT, 1f
+	/* Asynchronous TCF occurred for TTBR0 access, set the TI flag */
+	orr	\flgs, \flgs, #_TIF_MTE_ASYNC_FAULT
+	str	\flgs, [tsk, #TSK_TI_FLAGS]
+	msr_s	SYS_TFSRE0_EL1, xzr
+1:
+#endif
+	.endm
+
+	/* Clear the MTE asynchronous tag check faults */
+	.macro clear_mte_async_tcf
+#ifdef CONFIG_ARM64_MTE
+alternative_if ARM64_MTE
+	dsb	ish
+	msr_s	SYS_TFSRE0_EL1, xzr
+alternative_else_nop_endif
 #endif
 	.endm
 
@@ -170,19 +194,6 @@
 	stp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
-	.if	\regsize == 32
-	/*
-	 * If we're returning from a 32-bit task on a system affected by
-	 * 1418040 then re-enable userspace access to the virtual counter.
-	 */
-#ifdef CONFIG_ARM64_ERRATUM_1418040
-alternative_if ARM64_WORKAROUND_1418040
-	mrs	x0, cntkctl_el1
-	orr	x0, x0, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
-	msr	cntkctl_el1, x0
-alternative_else_nop_endif
-#endif
-	.endif
 	clear_gp_regs
 	mrs	x21, sp_el0
 	ldr_this_cpu	tsk, __entry_task, x20
@@ -195,6 +206,8 @@
 	ldr	x19, [tsk, #TSK_TI_FLAGS]
 	disable_step_tsk x19, x20
 
+	/* Check for asynchronous tag check faults in user space */
+	check_mte_async_tcf x19, x22
 	apply_ssbd 1, x22, x23
 
 	ptrauth_keys_install_kernel tsk, x20, x22, x23
@@ -246,6 +259,13 @@
 	str	x20, [sp, #S_PMR_SAVE]
 alternative_else_nop_endif
 
+	/* Re-enable tag checking (TCO set on exception entry) */
+#ifdef CONFIG_ARM64_MTE
+alternative_if ARM64_MTE
+	SET_PSTATE_TCO(0)
+alternative_else_nop_endif
+#endif
+
 	/*
 	 * Registers that may be useful after this macro is invoked:
 	 *
@@ -294,14 +314,6 @@
 	tst	x22, #PSR_MODE32_BIT		// native task?
 	b.eq	3f
 
-#ifdef CONFIG_ARM64_ERRATUM_1418040
-alternative_if ARM64_WORKAROUND_1418040
-	mrs	x0, cntkctl_el1
-	bic	x0, x0, #2			// ARCH_TIMER_USR_VCT_ACCESS_EN
-	msr	cntkctl_el1, x0
-alternative_else_nop_endif
-#endif
-
 #ifdef CONFIG_ARM64_ERRATUM_845719
 alternative_if ARM64_WORKAROUND_845719
 #ifdef CONFIG_PID_IN_CONTEXTIDR
@@ -718,11 +730,9 @@
 	bl	trace_hardirqs_off
 #endif
 
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 	tbz	x22, #55, 1f
 	bl	do_el0_irq_bp_hardening
 1:
-#endif
 	irq_handler
 
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -765,6 +775,8 @@
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
 finish_ret_to_user:
+	/* Ignore asynchronous tag check faults in the uaccess routines */
+	clear_mte_async_tcf
 	enable_step_tsk x1, x2
 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK
 	bl	stackleak_erase
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 55c8f3e..a6d688c 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -32,9 +32,11 @@
 #include <linux/swab.h>
 
 #include <asm/esr.h>
+#include <asm/exception.h>
 #include <asm/fpsimd.h>
 #include <asm/cpufeature.h>
 #include <asm/cputype.h>
+#include <asm/neon.h>
 #include <asm/processor.h>
 #include <asm/simd.h>
 #include <asm/sigcontext.h>
@@ -312,7 +314,7 @@
 				 * re-enter user with corrupt state.
 				 * There's no way to recover, so kill it:
 				 */
-				force_signal_inject(SIGKILL, SI_KERNEL, 0);
+				force_signal_inject(SIGKILL, SI_KERNEL, 0, 0);
 				return;
 			}
 
@@ -928,7 +930,7 @@
  * the SVE access trap will be disabled the next time this task
  * reaches ret_to_user.
  *
- * TIF_SVE should be clear on entry: otherwise, task_fpsimd_load()
+ * TIF_SVE should be clear on entry: otherwise, fpsimd_restore_current_state()
  * would have disabled the SVE access trap for userspace during
  * ret_to_user, making an SVE access trap impossible in that case.
  */
@@ -936,7 +938,7 @@
 {
 	/* Even if we chose not to use SVE, the hardware could still trap: */
 	if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) {
-		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
 		return;
 	}
 
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 037421c..d8d9caf 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -36,14 +36,10 @@
 
 #include "efi-header.S"
 
-#define __PHYS_OFFSET	(KERNEL_START - TEXT_OFFSET)
+#define __PHYS_OFFSET	KERNEL_START
 
-#if (TEXT_OFFSET & 0xfff) != 0
-#error TEXT_OFFSET must be at least 4KB aligned
-#elif (PAGE_OFFSET & 0x1fffff) != 0
+#if (PAGE_OFFSET & 0x1fffff) != 0
 #error PAGE_OFFSET must be at least 2MB aligned
-#elif TEXT_OFFSET > 0x1fffff
-#error TEXT_OFFSET must be less than 2MB
 #endif
 
 /*
@@ -55,7 +51,7 @@
  *   x0 = physical address to the FDT blob.
  *
  * This code is mostly position independent so you call this at
- * __pa(PAGE_OFFSET + TEXT_OFFSET).
+ * __pa(PAGE_OFFSET).
  *
  * Note that the callee-saved registers are used for storing variables
  * that are useful before the MMU is enabled. The allocations are described
@@ -77,7 +73,7 @@
 	b	primary_entry			// branch to kernel start, magic
 	.long	0				// reserved
 #endif
-	le64sym	_kernel_offset_le		// Image load offset from start of RAM, little-endian
+	.quad	0				// Image load offset from start of RAM, little-endian
 	le64sym	_kernel_size_le			// Effective size of kernel image, little-endian
 	le64sym	_kernel_flags_le		// Informative flags, little-endian
 	.quad	0				// reserved
@@ -382,7 +378,7 @@
 	 * Map the kernel image (starting with PHYS_OFFSET).
 	 */
 	adrp	x0, init_pg_dir
-	mov_q	x5, KIMAGE_VADDR + TEXT_OFFSET	// compile time __va(_text)
+	mov_q	x5, KIMAGE_VADDR		// compile time __va(_text)
 	add	x5, x5, x23			// add KASLR displacement
 	mov	x4, PTRS_PER_PGD
 	adrp	x6, _end			// runtime __pa(_end)
@@ -474,7 +470,7 @@
 
 	.pushsection ".rodata", "a"
 SYM_DATA_START(kimage_vaddr)
-	.quad		_text - TEXT_OFFSET
+	.quad		_text
 SYM_DATA_END(kimage_vaddr)
 EXPORT_SYMBOL(kimage_vaddr)
 	.popsection
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 68e1415..4200377 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -21,7 +21,6 @@
 #include <linux/sched.h>
 #include <linux/suspend.h>
 #include <linux/utsname.h>
-#include <linux/version.h>
 
 #include <asm/barrier.h>
 #include <asm/cacheflush.h>
@@ -31,6 +30,7 @@
 #include <asm/kexec.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
+#include <asm/mte.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/sections.h>
@@ -285,6 +285,117 @@
 
 #define dcache_clean_range(start, end)	__flush_dcache_area(start, (end - start))
 
+#ifdef CONFIG_ARM64_MTE
+
+static DEFINE_XARRAY(mte_pages);
+
+static int save_tags(struct page *page, unsigned long pfn)
+{
+	void *tag_storage, *ret;
+
+	tag_storage = mte_allocate_tag_storage();
+	if (!tag_storage)
+		return -ENOMEM;
+
+	mte_save_page_tags(page_address(page), tag_storage);
+
+	ret = xa_store(&mte_pages, pfn, tag_storage, GFP_KERNEL);
+	if (WARN(xa_is_err(ret), "Failed to store MTE tags")) {
+		mte_free_tag_storage(tag_storage);
+		return xa_err(ret);
+	} else if (WARN(ret, "swsusp: %s: Duplicate entry", __func__)) {
+		mte_free_tag_storage(ret);
+	}
+
+	return 0;
+}
+
+static void swsusp_mte_free_storage(void)
+{
+	XA_STATE(xa_state, &mte_pages, 0);
+	void *tags;
+
+	xa_lock(&mte_pages);
+	xas_for_each(&xa_state, tags, ULONG_MAX) {
+		mte_free_tag_storage(tags);
+	}
+	xa_unlock(&mte_pages);
+
+	xa_destroy(&mte_pages);
+}
+
+static int swsusp_mte_save_tags(void)
+{
+	struct zone *zone;
+	unsigned long pfn, max_zone_pfn;
+	int ret = 0;
+	int n = 0;
+
+	if (!system_supports_mte())
+		return 0;
+
+	for_each_populated_zone(zone) {
+		max_zone_pfn = zone_end_pfn(zone);
+		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
+			struct page *page = pfn_to_online_page(pfn);
+
+			if (!page)
+				continue;
+
+			if (!test_bit(PG_mte_tagged, &page->flags))
+				continue;
+
+			ret = save_tags(page, pfn);
+			if (ret) {
+				swsusp_mte_free_storage();
+				goto out;
+			}
+
+			n++;
+		}
+	}
+	pr_info("Saved %d MTE pages\n", n);
+
+out:
+	return ret;
+}
+
+static void swsusp_mte_restore_tags(void)
+{
+	XA_STATE(xa_state, &mte_pages, 0);
+	int n = 0;
+	void *tags;
+
+	xa_lock(&mte_pages);
+	xas_for_each(&xa_state, tags, ULONG_MAX) {
+		unsigned long pfn = xa_state.xa_index;
+		struct page *page = pfn_to_online_page(pfn);
+
+		mte_restore_page_tags(page_address(page), tags);
+
+		mte_free_tag_storage(tags);
+		n++;
+	}
+	xa_unlock(&mte_pages);
+
+	pr_info("Restored %d MTE pages\n", n);
+
+	xa_destroy(&mte_pages);
+}
+
+#else	/* CONFIG_ARM64_MTE */
+
+static int swsusp_mte_save_tags(void)
+{
+	return 0;
+}
+
+static void swsusp_mte_restore_tags(void)
+{
+}
+
+#endif	/* CONFIG_ARM64_MTE */
+
 int swsusp_arch_suspend(void)
 {
 	int ret = 0;
@@ -302,6 +413,10 @@
 		/* make the crash dump kernel image visible/saveable */
 		crash_prepare_suspend();
 
+		ret = swsusp_mte_save_tags();
+		if (ret)
+			return ret;
+
 		sleep_cpu = smp_processor_id();
 		ret = swsusp_save();
 	} else {
@@ -315,6 +430,8 @@
 			dcache_clean_range(__hyp_text_start, __hyp_text_end);
 		}
 
+		swsusp_mte_restore_tags();
+
 		/* make the crash dump kernel image protected again */
 		crash_post_resume();
 
@@ -332,11 +449,7 @@
 		 * mitigation off behind our back, let's set the state
 		 * to what we expect it to be.
 		 */
-		switch (arm64_get_ssbd_state()) {
-		case ARM64_SSBD_FORCE_ENABLE:
-		case ARM64_SSBD_KERNEL:
-			arm64_set_ssbd_mitigation(true);
-		}
+		spectre_v4_enable_mitigation(NULL);
 	}
 
 	local_daif_restore(flags);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index af234a1..712e97c 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -257,7 +257,7 @@
 		 * level.
 		 */
 		enable_debug_monitors(dbg_el);
-		/* Fall through */
+		fallthrough;
 	case HW_BREAKPOINT_RESTORE:
 		/* Setup the address register. */
 		write_wb_reg(val_reg, i, info->address);
@@ -541,13 +541,13 @@
 			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 				break;
 
-			/* Fallthrough */
+			fallthrough;
 		case 3:
 			/* Allow single byte watchpoint. */
 			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 				break;
 
-			/* Fallthrough */
+			fallthrough;
 		default:
 			return -EINVAL;
 		}
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 9e897c5..d0f3f35 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -64,12 +64,10 @@
 #define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym;
 
 /* Alternative callbacks for init-time patching of nVHE hyp code. */
-KVM_NVHE_ALIAS(arm64_enable_wa2_handling);
 KVM_NVHE_ALIAS(kvm_patch_vector_branch);
 KVM_NVHE_ALIAS(kvm_update_va_mask);
 
 /* Global kernel state accessed by nVHE hyp code. */
-KVM_NVHE_ALIAS(arm64_ssbd_callback_required);
 KVM_NVHE_ALIAS(kvm_host_data);
 KVM_NVHE_ALIAS(kvm_vgic_global_state);
 
@@ -103,6 +101,10 @@
 KVM_NVHE_ALIAS(gic_pmr_sync);
 #endif
 
+/* EL2 exception handling */
+KVM_NVHE_ALIAS(__start___kvm_ex_table);
+KVM_NVHE_ALIAS(__stop___kvm_ex_table);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h
index c7d38c6..7bc3ba8 100644
--- a/arch/arm64/kernel/image.h
+++ b/arch/arm64/kernel/image.h
@@ -62,7 +62,6 @@
  */
 #define HEAD_SYMBOLS						\
 	DEFINE_IMAGE_LE64(_kernel_size_le, _end - _text);	\
-	DEFINE_IMAGE_LE64(_kernel_offset_le, TEXT_OFFSET);	\
 	DEFINE_IMAGE_LE64(_kernel_flags_le, __HEAD_FLAGS);
 
 #endif /* __ARM64_KERNEL_IMAGE_H */
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index a107375..6c0de2f 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -60,16 +60,10 @@
 	case AARCH64_INSN_HINT_XPACLRI:
 	case AARCH64_INSN_HINT_PACIA_1716:
 	case AARCH64_INSN_HINT_PACIB_1716:
-	case AARCH64_INSN_HINT_AUTIA_1716:
-	case AARCH64_INSN_HINT_AUTIB_1716:
 	case AARCH64_INSN_HINT_PACIAZ:
 	case AARCH64_INSN_HINT_PACIASP:
 	case AARCH64_INSN_HINT_PACIBZ:
 	case AARCH64_INSN_HINT_PACIBSP:
-	case AARCH64_INSN_HINT_AUTIAZ:
-	case AARCH64_INSN_HINT_AUTIASP:
-	case AARCH64_INSN_HINT_AUTIBZ:
-	case AARCH64_INSN_HINT_AUTIBSP:
 	case AARCH64_INSN_HINT_BTI:
 	case AARCH64_INSN_HINT_BTIC:
 	case AARCH64_INSN_HINT_BTIJ:
@@ -176,7 +170,7 @@
 
 bool __kprobes aarch64_insn_is_branch(u32 insn)
 {
-	/* b, bl, cb*, tb*, b.cond, br, blr */
+	/* b, bl, cb*, tb*, ret*, b.cond, br*, blr* */
 
 	return aarch64_insn_is_b(insn) ||
 		aarch64_insn_is_bl(insn) ||
@@ -185,8 +179,11 @@
 		aarch64_insn_is_tbz(insn) ||
 		aarch64_insn_is_tbnz(insn) ||
 		aarch64_insn_is_ret(insn) ||
+		aarch64_insn_is_ret_auth(insn) ||
 		aarch64_insn_is_br(insn) ||
+		aarch64_insn_is_br_auth(insn) ||
 		aarch64_insn_is_blr(insn) ||
+		aarch64_insn_is_blr_auth(insn) ||
 		aarch64_insn_is_bcond(insn);
 }
 
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index 0ce3a28..2e22443 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -305,8 +305,7 @@
 			mod->arch.core.plt_shndx = i;
 		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
 			mod->arch.init.plt_shndx = i;
-		else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
-			 !strcmp(secstrings + sechdrs[i].sh_name,
+		else if (!strcmp(secstrings + sechdrs[i].sh_name,
 				 ".text.ftrace_trampoline"))
 			tramp = sechdrs + i;
 		else if (sechdrs[i].sh_type == SHT_SYMTAB)
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 1cd1a4d..2a1ad95 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -315,21 +315,21 @@
 		/* MOVW instruction relocations. */
 		case R_AARCH64_MOVW_UABS_G0_NC:
 			overflow_check = false;
-			/* Fall through */
+			fallthrough;
 		case R_AARCH64_MOVW_UABS_G0:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
 					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G1_NC:
 			overflow_check = false;
-			/* Fall through */
+			fallthrough;
 		case R_AARCH64_MOVW_UABS_G1:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
 					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G2_NC:
 			overflow_check = false;
-			/* Fall through */
+			fallthrough;
 		case R_AARCH64_MOVW_UABS_G2:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
 					      AARCH64_INSN_IMM_MOVKZ);
@@ -397,7 +397,7 @@
 			break;
 		case R_AARCH64_ADR_PREL_PG_HI21_NC:
 			overflow_check = false;
-			/* Fall through */
+			fallthrough;
 		case R_AARCH64_ADR_PREL_PG_HI21:
 			ovf = reloc_insn_adrp(me, sechdrs, loc, val);
 			if (ovf && ovf != -ERANGE)
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
new file mode 100644
index 0000000..52a0638
--- /dev/null
+++ b/arch/arm64/kernel/mte.c
@@ -0,0 +1,336 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/prctl.h>
+#include <linux/sched.h>
+#include <linux/sched/mm.h>
+#include <linux/string.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/thread_info.h>
+#include <linux/uio.h>
+
+#include <asm/cpufeature.h>
+#include <asm/mte.h>
+#include <asm/ptrace.h>
+#include <asm/sysreg.h>
+
+static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
+{
+	pte_t old_pte = READ_ONCE(*ptep);
+
+	if (check_swap && is_swap_pte(old_pte)) {
+		swp_entry_t entry = pte_to_swp_entry(old_pte);
+
+		if (!non_swap_entry(entry) && mte_restore_tags(entry, page))
+			return;
+	}
+
+	mte_clear_page_tags(page_address(page));
+}
+
+void mte_sync_tags(pte_t *ptep, pte_t pte)
+{
+	struct page *page = pte_page(pte);
+	long i, nr_pages = compound_nr(page);
+	bool check_swap = nr_pages == 1;
+
+	/* if PG_mte_tagged is set, tags have already been initialised */
+	for (i = 0; i < nr_pages; i++, page++) {
+		if (!test_and_set_bit(PG_mte_tagged, &page->flags))
+			mte_sync_page_tags(page, ptep, check_swap);
+	}
+}
+
+int memcmp_pages(struct page *page1, struct page *page2)
+{
+	char *addr1, *addr2;
+	int ret;
+
+	addr1 = page_address(page1);
+	addr2 = page_address(page2);
+	ret = memcmp(addr1, addr2, PAGE_SIZE);
+
+	if (!system_supports_mte() || ret)
+		return ret;
+
+	/*
+	 * If the page content is identical but at least one of the pages is
+	 * tagged, return non-zero to avoid KSM merging. If only one of the
+	 * pages is tagged, set_pte_at() may zero or change the tags of the
+	 * other page via mte_sync_tags().
+	 */
+	if (test_bit(PG_mte_tagged, &page1->flags) ||
+	    test_bit(PG_mte_tagged, &page2->flags))
+		return addr1 != addr2;
+
+	return ret;
+}
+
+static void update_sctlr_el1_tcf0(u64 tcf0)
+{
+	/* ISB required for the kernel uaccess routines */
+	sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF0_MASK, tcf0);
+	isb();
+}
+
+static void set_sctlr_el1_tcf0(u64 tcf0)
+{
+	/*
+	 * mte_thread_switch() checks current->thread.sctlr_tcf0 as an
+	 * optimisation. Disable preemption so that it does not see
+	 * the variable update before the SCTLR_EL1.TCF0 one.
+	 */
+	preempt_disable();
+	current->thread.sctlr_tcf0 = tcf0;
+	update_sctlr_el1_tcf0(tcf0);
+	preempt_enable();
+}
+
+static void update_gcr_el1_excl(u64 incl)
+{
+	u64 excl = ~incl & SYS_GCR_EL1_EXCL_MASK;
+
+	/*
+	 * Note that 'incl' is an include mask (controlled by the user via
+	 * prctl()) while GCR_EL1 accepts an exclude mask.
+	 * No need for ISB since this only affects EL0 currently, implicit
+	 * with ERET.
+	 */
+	sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, excl);
+}
+
+static void set_gcr_el1_excl(u64 incl)
+{
+	current->thread.gcr_user_incl = incl;
+	update_gcr_el1_excl(incl);
+}
+
+void flush_mte_state(void)
+{
+	if (!system_supports_mte())
+		return;
+
+	/* clear any pending asynchronous tag fault */
+	dsb(ish);
+	write_sysreg_s(0, SYS_TFSRE0_EL1);
+	clear_thread_flag(TIF_MTE_ASYNC_FAULT);
+	/* disable tag checking */
+	set_sctlr_el1_tcf0(SCTLR_EL1_TCF0_NONE);
+	/* reset tag generation mask */
+	set_gcr_el1_excl(0);
+}
+
+void mte_thread_switch(struct task_struct *next)
+{
+	if (!system_supports_mte())
+		return;
+
+	/* avoid expensive SCTLR_EL1 accesses if no change */
+	if (current->thread.sctlr_tcf0 != next->thread.sctlr_tcf0)
+		update_sctlr_el1_tcf0(next->thread.sctlr_tcf0);
+	update_gcr_el1_excl(next->thread.gcr_user_incl);
+}
+
+void mte_suspend_exit(void)
+{
+	if (!system_supports_mte())
+		return;
+
+	update_gcr_el1_excl(current->thread.gcr_user_incl);
+}
+
+long set_mte_ctrl(struct task_struct *task, unsigned long arg)
+{
+	u64 tcf0;
+	u64 gcr_incl = (arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT;
+
+	if (!system_supports_mte())
+		return 0;
+
+	switch (arg & PR_MTE_TCF_MASK) {
+	case PR_MTE_TCF_NONE:
+		tcf0 = SCTLR_EL1_TCF0_NONE;
+		break;
+	case PR_MTE_TCF_SYNC:
+		tcf0 = SCTLR_EL1_TCF0_SYNC;
+		break;
+	case PR_MTE_TCF_ASYNC:
+		tcf0 = SCTLR_EL1_TCF0_ASYNC;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (task != current) {
+		task->thread.sctlr_tcf0 = tcf0;
+		task->thread.gcr_user_incl = gcr_incl;
+	} else {
+		set_sctlr_el1_tcf0(tcf0);
+		set_gcr_el1_excl(gcr_incl);
+	}
+
+	return 0;
+}
+
+long get_mte_ctrl(struct task_struct *task)
+{
+	unsigned long ret;
+
+	if (!system_supports_mte())
+		return 0;
+
+	ret = task->thread.gcr_user_incl << PR_MTE_TAG_SHIFT;
+
+	switch (task->thread.sctlr_tcf0) {
+	case SCTLR_EL1_TCF0_NONE:
+		return PR_MTE_TCF_NONE;
+	case SCTLR_EL1_TCF0_SYNC:
+		ret |= PR_MTE_TCF_SYNC;
+		break;
+	case SCTLR_EL1_TCF0_ASYNC:
+		ret |= PR_MTE_TCF_ASYNC;
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * Access MTE tags in another process' address space as given in mm. Update
+ * the number of tags copied. Return 0 if any tags copied, error otherwise.
+ * Inspired by __access_remote_vm().
+ */
+static int __access_remote_tags(struct mm_struct *mm, unsigned long addr,
+				struct iovec *kiov, unsigned int gup_flags)
+{
+	struct vm_area_struct *vma;
+	void __user *buf = kiov->iov_base;
+	size_t len = kiov->iov_len;
+	int ret;
+	int write = gup_flags & FOLL_WRITE;
+
+	if (!access_ok(buf, len))
+		return -EFAULT;
+
+	if (mmap_read_lock_killable(mm))
+		return -EIO;
+
+	while (len) {
+		unsigned long tags, offset;
+		void *maddr;
+		struct page *page = NULL;
+
+		ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page,
+					    &vma, NULL);
+		if (ret <= 0)
+			break;
+
+		/*
+		 * Only copy tags if the page has been mapped as PROT_MTE
+		 * (PG_mte_tagged set). Otherwise the tags are not valid and
+		 * not accessible to user. Moreover, an mprotect(PROT_MTE)
+		 * would cause the existing tags to be cleared if the page
+		 * was never mapped with PROT_MTE.
+		 */
+		if (!test_bit(PG_mte_tagged, &page->flags)) {
+			ret = -EOPNOTSUPP;
+			put_page(page);
+			break;
+		}
+
+		/* limit access to the end of the page */
+		offset = offset_in_page(addr);
+		tags = min(len, (PAGE_SIZE - offset) / MTE_GRANULE_SIZE);
+
+		maddr = page_address(page);
+		if (write) {
+			tags = mte_copy_tags_from_user(maddr + offset, buf, tags);
+			set_page_dirty_lock(page);
+		} else {
+			tags = mte_copy_tags_to_user(buf, maddr + offset, tags);
+		}
+		put_page(page);
+
+		/* error accessing the tracer's buffer */
+		if (!tags)
+			break;
+
+		len -= tags;
+		buf += tags;
+		addr += tags * MTE_GRANULE_SIZE;
+	}
+	mmap_read_unlock(mm);
+
+	/* return an error if no tags copied */
+	kiov->iov_len = buf - kiov->iov_base;
+	if (!kiov->iov_len) {
+		/* check for error accessing the tracee's address space */
+		if (ret <= 0)
+			return -EIO;
+		else
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+/*
+ * Copy MTE tags in another process' address space at 'addr' to/from tracer's
+ * iovec buffer. Return 0 on success. Inspired by ptrace_access_vm().
+ */
+static int access_remote_tags(struct task_struct *tsk, unsigned long addr,
+			      struct iovec *kiov, unsigned int gup_flags)
+{
+	struct mm_struct *mm;
+	int ret;
+
+	mm = get_task_mm(tsk);
+	if (!mm)
+		return -EPERM;
+
+	if (!tsk->ptrace || (current != tsk->parent) ||
+	    ((get_dumpable(mm) != SUID_DUMP_USER) &&
+	     !ptracer_capable(tsk, mm->user_ns))) {
+		mmput(mm);
+		return -EPERM;
+	}
+
+	ret = __access_remote_tags(mm, addr, kiov, gup_flags);
+	mmput(mm);
+
+	return ret;
+}
+
+int mte_ptrace_copy_tags(struct task_struct *child, long request,
+			 unsigned long addr, unsigned long data)
+{
+	int ret;
+	struct iovec kiov;
+	struct iovec __user *uiov = (void __user *)data;
+	unsigned int gup_flags = FOLL_FORCE;
+
+	if (!system_supports_mte())
+		return -EIO;
+
+	if (get_user(kiov.iov_base, &uiov->iov_base) ||
+	    get_user(kiov.iov_len, &uiov->iov_len))
+		return -EFAULT;
+
+	if (request == PTRACE_POKEMTETAGS)
+		gup_flags |= FOLL_WRITE;
+
+	/* align addr to the MTE tag granule */
+	addr &= MTE_GRANULE_MASK;
+
+	ret = access_remote_tags(child, addr, &kiov, gup_flags);
+	if (!ret)
+		ret = put_user(kiov.iov_len, &uiov->iov_len);
+
+	return ret;
+}
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 295d664..c07d7a0 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -50,16 +50,19 @@
 	struct pv_time_stolen_time_region *reg;
 
 	reg = per_cpu_ptr(&stolen_time_region, cpu);
-	if (!reg->kaddr) {
-		pr_warn_once("stolen time enabled but not configured for cpu %d\n",
-			     cpu);
+
+	/*
+	 * paravirt_steal_clock() may be called before the CPU
+	 * online notification callback runs. Until the callback
+	 * has run we just return zero.
+	 */
+	if (!reg->kaddr)
 		return 0;
-	}
 
 	return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
 }
 
-static int stolen_time_dying_cpu(unsigned int cpu)
+static int stolen_time_cpu_down_prepare(unsigned int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 
@@ -73,7 +76,7 @@
 	return 0;
 }
 
-static int init_stolen_time_cpu(unsigned int cpu)
+static int stolen_time_cpu_online(unsigned int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 	struct arm_smccc_res res;
@@ -103,19 +106,20 @@
 	return 0;
 }
 
-static int pv_time_init_stolen_time(void)
+static int __init pv_time_init_stolen_time(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING,
-				"hypervisor/arm/pvtime:starting",
-				init_stolen_time_cpu, stolen_time_dying_cpu);
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				"hypervisor/arm/pvtime:online",
+				stolen_time_cpu_online,
+				stolen_time_cpu_down_prepare);
 	if (ret < 0)
 		return ret;
 	return 0;
 }
 
-static bool has_pv_steal_clock(void)
+static bool __init has_pv_steal_clock(void)
 {
 	struct arm_smccc_res res;
 
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index b0e03e0..88ff471 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -137,11 +137,11 @@
  * whist unwinding the stackframe and is like a subroutine return so we use
  * the PC.
  */
-static int callchain_trace(struct stackframe *frame, void *data)
+static bool callchain_trace(void *data, unsigned long pc)
 {
 	struct perf_callchain_entry_ctx *entry = data;
-	perf_callchain_store(entry, frame->pc);
-	return 0;
+	perf_callchain_store(entry, pc);
+	return true;
 }
 
 void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 462f9a9..3605f77a 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -69,6 +69,9 @@
 	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL,
 	[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1I_TLB,
 
+	[C(LL)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD,
+	[C(LL)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_LL_CACHE_RD,
+
 	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_BR_PRED,
 	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
 };
@@ -302,13 +305,33 @@
 	.attrs = armv8_pmuv3_format_attrs,
 };
 
+static ssize_t slots_show(struct device *dev, struct device_attribute *attr,
+			  char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+	u32 slots = cpu_pmu->reg_pmmir & ARMV8_PMU_SLOTS_MASK;
+
+	return snprintf(page, PAGE_SIZE, "0x%08x\n", slots);
+}
+
+static DEVICE_ATTR_RO(slots);
+
+static struct attribute *armv8_pmuv3_caps_attrs[] = {
+	&dev_attr_slots.attr,
+	NULL,
+};
+
+static struct attribute_group armv8_pmuv3_caps_attr_group = {
+	.name = "caps",
+	.attrs = armv8_pmuv3_caps_attrs,
+};
+
 /*
  * Perf Events' indices
  */
 #define	ARMV8_IDX_CYCLE_COUNTER	0
 #define	ARMV8_IDX_COUNTER0	1
-#define	ARMV8_IDX_COUNTER_LAST(cpu_pmu) \
-	(ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
 
 
 /*
@@ -348,6 +371,73 @@
 #define	ARMV8_IDX_TO_COUNTER(x)	\
 	(((x) - ARMV8_IDX_COUNTER0) & ARMV8_PMU_COUNTER_MASK)
 
+/*
+ * This code is really good
+ */
+
+#define PMEVN_CASE(n, case_macro) \
+	case n: case_macro(n); break
+
+#define PMEVN_SWITCH(x, case_macro)				\
+	do {							\
+		switch (x) {					\
+		PMEVN_CASE(0,  case_macro);			\
+		PMEVN_CASE(1,  case_macro);			\
+		PMEVN_CASE(2,  case_macro);			\
+		PMEVN_CASE(3,  case_macro);			\
+		PMEVN_CASE(4,  case_macro);			\
+		PMEVN_CASE(5,  case_macro);			\
+		PMEVN_CASE(6,  case_macro);			\
+		PMEVN_CASE(7,  case_macro);			\
+		PMEVN_CASE(8,  case_macro);			\
+		PMEVN_CASE(9,  case_macro);			\
+		PMEVN_CASE(10, case_macro);			\
+		PMEVN_CASE(11, case_macro);			\
+		PMEVN_CASE(12, case_macro);			\
+		PMEVN_CASE(13, case_macro);			\
+		PMEVN_CASE(14, case_macro);			\
+		PMEVN_CASE(15, case_macro);			\
+		PMEVN_CASE(16, case_macro);			\
+		PMEVN_CASE(17, case_macro);			\
+		PMEVN_CASE(18, case_macro);			\
+		PMEVN_CASE(19, case_macro);			\
+		PMEVN_CASE(20, case_macro);			\
+		PMEVN_CASE(21, case_macro);			\
+		PMEVN_CASE(22, case_macro);			\
+		PMEVN_CASE(23, case_macro);			\
+		PMEVN_CASE(24, case_macro);			\
+		PMEVN_CASE(25, case_macro);			\
+		PMEVN_CASE(26, case_macro);			\
+		PMEVN_CASE(27, case_macro);			\
+		PMEVN_CASE(28, case_macro);			\
+		PMEVN_CASE(29, case_macro);			\
+		PMEVN_CASE(30, case_macro);			\
+		default: WARN(1, "Invalid PMEV* index\n");	\
+		}						\
+	} while (0)
+
+#define RETURN_READ_PMEVCNTRN(n) \
+	return read_sysreg(pmevcntr##n##_el0)
+static unsigned long read_pmevcntrn(int n)
+{
+	PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN);
+	return 0;
+}
+
+#define WRITE_PMEVCNTRN(n) \
+	write_sysreg(val, pmevcntr##n##_el0)
+static void write_pmevcntrn(int n, unsigned long val)
+{
+	PMEVN_SWITCH(n, WRITE_PMEVCNTRN);
+}
+
+#define WRITE_PMEVTYPERN(n) \
+	write_sysreg(val, pmevtyper##n##_el0)
+static void write_pmevtypern(int n, unsigned long val)
+{
+	PMEVN_SWITCH(n, WRITE_PMEVTYPERN);
+}
+
 static inline u32 armv8pmu_pmcr_read(void)
 {
 	return read_sysreg(pmcr_el0);
@@ -365,28 +455,16 @@
 	return pmovsr & ARMV8_PMU_OVERFLOWED_MASK;
 }
 
-static inline int armv8pmu_counter_valid(struct arm_pmu *cpu_pmu, int idx)
-{
-	return idx >= ARMV8_IDX_CYCLE_COUNTER &&
-		idx <= ARMV8_IDX_COUNTER_LAST(cpu_pmu);
-}
-
 static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
 {
 	return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
 }
 
-static inline void armv8pmu_select_counter(int idx)
+static inline u32 armv8pmu_read_evcntr(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
-	write_sysreg(counter, pmselr_el0);
-	isb();
-}
 
-static inline u64 armv8pmu_read_evcntr(int idx)
-{
-	armv8pmu_select_counter(idx);
-	return read_sysreg(pmxevcntr_el0);
+	return read_pmevcntrn(counter);
 }
 
 static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
@@ -440,15 +518,11 @@
 
 static u64 armv8pmu_read_counter(struct perf_event *event)
 {
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 	u64 value = 0;
 
-	if (!armv8pmu_counter_valid(cpu_pmu, idx))
-		pr_err("CPU%u reading wrong counter %d\n",
-			smp_processor_id(), idx);
-	else if (idx == ARMV8_IDX_CYCLE_COUNTER)
+	if (idx == ARMV8_IDX_CYCLE_COUNTER)
 		value = read_sysreg(pmccntr_el0);
 	else
 		value = armv8pmu_read_hw_counter(event);
@@ -458,8 +532,9 @@
 
 static inline void armv8pmu_write_evcntr(int idx, u64 value)
 {
-	armv8pmu_select_counter(idx);
-	write_sysreg(value, pmxevcntr_el0);
+	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
+
+	write_pmevcntrn(counter, value);
 }
 
 static inline void armv8pmu_write_hw_counter(struct perf_event *event,
@@ -477,16 +552,12 @@
 
 static void armv8pmu_write_counter(struct perf_event *event, u64 value)
 {
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
 	value = armv8pmu_bias_long_counter(event, value);
 
-	if (!armv8pmu_counter_valid(cpu_pmu, idx))
-		pr_err("CPU%u writing wrong counter %d\n",
-			smp_processor_id(), idx);
-	else if (idx == ARMV8_IDX_CYCLE_COUNTER)
+	if (idx == ARMV8_IDX_CYCLE_COUNTER)
 		write_sysreg(value, pmccntr_el0);
 	else
 		armv8pmu_write_hw_counter(event, value);
@@ -494,9 +565,10 @@
 
 static inline void armv8pmu_write_evtype(int idx, u32 val)
 {
-	armv8pmu_select_counter(idx);
+	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
+
 	val &= ARMV8_PMU_EVTYPE_MASK;
-	write_sysreg(val, pmxevtyper_el0);
+	write_pmevtypern(counter, val);
 }
 
 static inline void armv8pmu_write_event_type(struct perf_event *event)
@@ -516,7 +588,10 @@
 		armv8pmu_write_evtype(idx - 1, hwc->config_base);
 		armv8pmu_write_evtype(idx, chain_evt);
 	} else {
-		armv8pmu_write_evtype(idx, hwc->config_base);
+		if (idx == ARMV8_IDX_CYCLE_COUNTER)
+			write_sysreg(hwc->config_base, pmccfiltr_el0);
+		else
+			armv8pmu_write_evtype(idx, hwc->config_base);
 	}
 }
 
@@ -532,6 +607,11 @@
 
 static inline void armv8pmu_enable_counter(u32 mask)
 {
+	/*
+	 * Make sure event configuration register writes are visible before we
+	 * enable the counter.
+	 * */
+	isb();
 	write_sysreg(mask, pmcntenset_el0);
 }
 
@@ -550,6 +630,11 @@
 static inline void armv8pmu_disable_counter(u32 mask)
 {
 	write_sysreg(mask, pmcntenclr_el0);
+	/*
+	 * Make sure the effects of disabling the counter are visible before we
+	 * start configuring the event.
+	 */
+	isb();
 }
 
 static inline void armv8pmu_disable_event_counter(struct perf_event *event)
@@ -606,15 +691,10 @@
 
 static void armv8pmu_enable_event(struct perf_event *event)
 {
-	unsigned long flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-
 	/*
 	 * Enable counter and interrupt, and set the counter to count
 	 * the event that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/*
 	 * Disable counter
@@ -622,7 +702,7 @@
 	armv8pmu_disable_event_counter(event);
 
 	/*
-	 * Set event (if destined for PMNx counters).
+	 * Set event.
 	 */
 	armv8pmu_write_event_type(event);
 
@@ -635,21 +715,10 @@
 	 * Enable counter
 	 */
 	armv8pmu_enable_event_counter(event);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv8pmu_disable_event(struct perf_event *event)
 {
-	unsigned long flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-
-	/*
-	 * Disable counter and interrupt
-	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
-
 	/*
 	 * Disable counter
 	 */
@@ -659,30 +728,18 @@
 	 * Disable interrupt for this counter
 	 */
 	armv8pmu_disable_event_irq(event);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv8pmu_start(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Enable all counters */
 	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Disable all counters */
 	armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
@@ -735,20 +792,16 @@
 		if (!armpmu_event_set_period(event))
 			continue;
 
+		/*
+		 * Perf event overflow will queue the processing of the event as
+		 * an irq_work which will be taken care of in the handling of
+		 * IPI_IRQ_WORK.
+		 */
 		if (perf_event_overflow(event, &data, regs))
 			cpu_pmu->disable(event);
 	}
 	armv8pmu_start(cpu_pmu);
 
-	/*
-	 * Handle the pending perf events.
-	 *
-	 * Note: this call *must* be run with interrupts disabled. For
-	 * platforms that can have the PMU interrupts raised as an NMI, this
-	 * will not work.
-	 */
-	irq_work_run();
-
 	return IRQ_HANDLED;
 }
 
@@ -997,6 +1050,12 @@
 
 	bitmap_from_arr32(cpu_pmu->pmceid_ext_bitmap,
 			     pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+
+	/* store PMMIR_EL1 register for sysfs */
+	if (pmuver >= ID_AA64DFR0_PMUVER_8_4 && (pmceid_raw[1] & BIT(31)))
+		cpu_pmu->reg_pmmir = read_cpuid(PMMIR_EL1);
+	else
+		cpu_pmu->reg_pmmir = 0;
 }
 
 static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
@@ -1019,7 +1078,8 @@
 static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 			  int (*map_event)(struct perf_event *event),
 			  const struct attribute_group *events,
-			  const struct attribute_group *format)
+			  const struct attribute_group *format,
+			  const struct attribute_group *caps)
 {
 	int ret = armv8pmu_probe_pmu(cpu_pmu);
 	if (ret)
@@ -1044,104 +1104,112 @@
 			events : &armv8_pmuv3_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = format ?
 			format : &armv8_pmuv3_format_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = caps ?
+			caps : &armv8_pmuv3_caps_attr_group;
 
 	return 0;
 }
 
+static int armv8_pmu_init_nogroups(struct arm_pmu *cpu_pmu, char *name,
+				   int (*map_event)(struct perf_event *event))
+{
+	return armv8_pmu_init(cpu_pmu, name, map_event, NULL, NULL, NULL);
+}
+
 static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_pmuv3",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_pmuv3",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a34_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a34",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a34",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a35",
-			      armv8_a53_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a35",
+				       armv8_a53_map_event);
 }
 
 static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a53",
-			      armv8_a53_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a53",
+				       armv8_a53_map_event);
 }
 
 static int armv8_a55_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a55",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a55",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a57",
-			      armv8_a57_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a57",
+				       armv8_a57_map_event);
 }
 
 static int armv8_a65_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a65",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a65",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a72",
-			      armv8_a57_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a72",
+				       armv8_a57_map_event);
 }
 
 static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a73",
-			      armv8_a73_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a73",
+				       armv8_a73_map_event);
 }
 
 static int armv8_a75_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a75",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a75",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a76_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a76",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a76",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a77_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a77",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a77",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_e1_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_neoverse_e1",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_neoverse_e1",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_n1_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_neoverse_n1",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_neoverse_n1",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cavium_thunder",
-			      armv8_thunder_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cavium_thunder",
+				       armv8_thunder_map_event);
 }
 
 static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_brcm_vulcan",
-			      armv8_vulcan_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_brcm_vulcan",
+				       armv8_vulcan_map_event);
 }
 
 static const struct of_device_id armv8_pmu_of_device_ids[] = {
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 666b225..94e8718 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -16,7 +16,7 @@
 
 	/*
 	 * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but
-	 * we're stuck with it for ABI compatability reasons.
+	 * we're stuck with it for ABI compatibility reasons.
 	 *
 	 * For a 32-bit consumer inspecting a 32-bit task, then it will look at
 	 * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h).
diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c
index 263d5fb..104101f 100644
--- a/arch/arm64/kernel/probes/decode-insn.c
+++ b/arch/arm64/kernel/probes/decode-insn.c
@@ -29,7 +29,8 @@
 		    aarch64_insn_is_msr_imm(insn) ||
 		    aarch64_insn_is_msr_reg(insn) ||
 		    aarch64_insn_is_exception(insn) ||
-		    aarch64_insn_is_eret(insn))
+		    aarch64_insn_is_eret(insn) ||
+		    aarch64_insn_is_eret_auth(insn))
 			return false;
 
 		/*
@@ -42,8 +43,10 @@
 			     != AARCH64_INSN_SPCLREG_DAIF;
 
 		/*
-		 * The HINT instruction is is problematic when single-stepping,
-		 * except for the NOP case.
+		 * The HINT instruction is steppable only if it is in whitelist
+		 * and the rest of other such instructions are blocked for
+		 * single stepping as they may cause exception or other
+		 * unintended behaviour.
 		 */
 		if (aarch64_insn_is_hint(insn))
 			return aarch64_insn_is_steppable_hint(insn);
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 84ec630..4784011 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -21,6 +21,7 @@
 #include <linux/lockdep.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
+#include <linux/nospec.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
 #include <linux/unistd.h>
@@ -52,6 +53,7 @@
 #include <asm/exec.h>
 #include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
+#include <asm/mte.h>
 #include <asm/processor.h>
 #include <asm/pointer_auth.h>
 #include <asm/stacktrace.h>
@@ -123,10 +125,8 @@
 	 * This should do all the clock switching and wait for interrupt
 	 * tricks
 	 */
-	trace_cpu_idle_rcuidle(1, smp_processor_id());
 	cpu_do_idle();
 	local_irq_enable();
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -241,7 +241,7 @@
 		const char *btype_str = btypes[(pstate & PSR_BTYPE_MASK) >>
 					       PSR_BTYPE_SHIFT];
 
-		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO BTYPE=%s)\n",
+		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO %cTCO BTYPE=%s)\n",
 			pstate,
 			pstate & PSR_N_BIT ? 'N' : 'n',
 			pstate & PSR_Z_BIT ? 'Z' : 'z',
@@ -253,6 +253,7 @@
 			pstate & PSR_F_BIT ? 'F' : 'f',
 			pstate & PSR_PAN_BIT ? '+' : '-',
 			pstate & PSR_UAO_BIT ? '+' : '-',
+			pstate & PSR_TCO_BIT ? '+' : '-',
 			btype_str);
 	}
 }
@@ -338,6 +339,7 @@
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
 	flush_tagged_addr_state();
+	flush_mte_state();
 }
 
 void release_thread(struct task_struct *dead_task)
@@ -370,6 +372,9 @@
 	dst->thread.sve_state = NULL;
 	clear_tsk_thread_flag(dst, TIF_SVE);
 
+	/* clear any pending asynchronous tag fault raised by the parent */
+	clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
+
 	return 0;
 }
 
@@ -423,8 +428,7 @@
 		    cpus_have_const_cap(ARM64_HAS_UAO))
 			childregs->pstate |= PSR_UAO_BIT;
 
-		if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
-			set_ssbs_bit(childregs);
+		spectre_v4_enable_task_mitigation(p);
 
 		if (system_uses_irq_prio_masking())
 			childregs->pmr_save = GIC_PRIO_IRQON;
@@ -474,8 +478,6 @@
  */
 static void ssbs_thread_switch(struct task_struct *next)
 {
-	struct pt_regs *regs = task_pt_regs(next);
-
 	/*
 	 * Nothing to do for kernel threads, but 'regs' may be junk
 	 * (e.g. idle task) so check the flags and bail early.
@@ -487,18 +489,10 @@
 	 * If all CPUs implement the SSBS extension, then we just need to
 	 * context-switch the PSTATE field.
 	 */
-	if (cpu_have_feature(cpu_feature(SSBS)))
+	if (cpus_have_const_cap(ARM64_SSBS))
 		return;
 
-	/* If the mitigation is enabled, then we leave SSBS clear. */
-	if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) ||
-	    test_tsk_thread_flag(next, TIF_SSBD))
-		return;
-
-	if (compat_user_mode(regs))
-		set_compat_ssbs_bit(regs);
-	else if (user_mode(regs))
-		set_ssbs_bit(regs);
+	spectre_v4_enable_task_mitigation(next);
 }
 
 /*
@@ -516,6 +510,39 @@
 }
 
 /*
+ * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT.
+ * Assuming the virtual counter is enabled at the beginning of times:
+ *
+ * - disable access when switching from a 64bit task to a 32bit task
+ * - enable access when switching from a 32bit task to a 64bit task
+ */
+static void erratum_1418040_thread_switch(struct task_struct *prev,
+					  struct task_struct *next)
+{
+	bool prev32, next32;
+	u64 val;
+
+	if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) &&
+	      cpus_have_const_cap(ARM64_WORKAROUND_1418040)))
+		return;
+
+	prev32 = is_compat_thread(task_thread_info(prev));
+	next32 = is_compat_thread(task_thread_info(next));
+
+	if (prev32 == next32)
+		return;
+
+	val = read_sysreg(cntkctl_el1);
+
+	if (!next32)
+		val |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+	else
+		val &= ~ARCH_TIMER_USR_VCT_ACCESS_EN;
+
+	write_sysreg(val, cntkctl_el1);
+}
+
+/*
  * Thread switching.
  */
 __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
@@ -530,6 +557,7 @@
 	entry_task_switch(next);
 	uao_thread_switch(next);
 	ssbs_thread_switch(next);
+	erratum_1418040_thread_switch(prev, next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
@@ -539,6 +567,13 @@
 	 */
 	dsb(ish);
 
+	/*
+	 * MTE thread switching must happen after the DSB above to ensure that
+	 * any asynchronous tag check faults have been logged in the TFSR*_EL1
+	 * registers.
+	 */
+	mte_thread_switch(next);
+
 	/* the actual thread switch */
 	last = cpu_switch_to(prev, next);
 
@@ -588,6 +623,11 @@
 	current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
 
 	ptrauth_thread_init_user(current);
+
+	if (task_spec_ssb_noexec(current)) {
+		arch_prctl_spec_ctrl_set(current, PR_SPEC_STORE_BYPASS,
+					 PR_SPEC_ENABLE);
+	}
 }
 
 #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
@@ -596,11 +636,18 @@
  */
 static unsigned int tagged_addr_disabled;
 
-long set_tagged_addr_ctrl(unsigned long arg)
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
 {
-	if (is_compat_task())
+	unsigned long valid_mask = PR_TAGGED_ADDR_ENABLE;
+	struct thread_info *ti = task_thread_info(task);
+
+	if (is_compat_thread(ti))
 		return -EINVAL;
-	if (arg & ~PR_TAGGED_ADDR_ENABLE)
+
+	if (system_supports_mte())
+		valid_mask |= PR_MTE_TCF_MASK | PR_MTE_TAG_MASK;
+
+	if (arg & ~valid_mask)
 		return -EINVAL;
 
 	/*
@@ -610,20 +657,28 @@
 	if (arg & PR_TAGGED_ADDR_ENABLE && tagged_addr_disabled)
 		return -EINVAL;
 
-	update_thread_flag(TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
+	if (set_mte_ctrl(task, arg) != 0)
+		return -EINVAL;
+
+	update_ti_thread_flag(ti, TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
 
 	return 0;
 }
 
-long get_tagged_addr_ctrl(void)
+long get_tagged_addr_ctrl(struct task_struct *task)
 {
-	if (is_compat_task())
+	long ret = 0;
+	struct thread_info *ti = task_thread_info(task);
+
+	if (is_compat_thread(ti))
 		return -EINVAL;
 
-	if (test_thread_flag(TIF_TAGGED_ADDR))
-		return PR_TAGGED_ADDR_ENABLE;
+	if (test_ti_thread_flag(ti, TIF_TAGGED_ADDR))
+		ret = PR_TAGGED_ADDR_ENABLE;
 
-	return 0;
+	ret |= get_mte_ctrl(task);
+
+	return ret;
 }
 
 /*
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
new file mode 100644
index 0000000..68b710f
--- /dev/null
+++ b/arch/arm64/kernel/proton-pack.c
@@ -0,0 +1,792 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Handle detection, reporting and mitigation of Spectre v1, v2 and v4, as
+ * detailed at:
+ *
+ *   https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability
+ *
+ * This code was originally written hastily under an awful lot of stress and so
+ * aspects of it are somewhat hacky. Unfortunately, changing anything in here
+ * instantly makes me feel ill. Thanks, Jann. Thann.
+ *
+ * Copyright (C) 2018 ARM Ltd, All Rights Reserved.
+ * Copyright (C) 2020 Google LLC
+ *
+ * "If there's something strange in your neighbourhood, who you gonna call?"
+ *
+ * Authors: Will Deacon <will@kernel.org> and Marc Zyngier <maz@kernel.org>
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/spectre.h>
+#include <asm/traps.h>
+
+/*
+ * We try to ensure that the mitigation state can never change as the result of
+ * onlining a late CPU.
+ */
+static void update_mitigation_state(enum mitigation_state *oldp,
+				    enum mitigation_state new)
+{
+	enum mitigation_state state;
+
+	do {
+		state = READ_ONCE(*oldp);
+		if (new <= state)
+			break;
+
+		/* Userspace almost certainly can't deal with this. */
+		if (WARN_ON(system_capabilities_finalized()))
+			break;
+	} while (cmpxchg_relaxed(oldp, state, new) != state);
+}
+
+/*
+ * Spectre v1.
+ *
+ * The kernel can't protect userspace for this one: it's each person for
+ * themselves. Advertise what we're doing and be done with it.
+ */
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+/*
+ * Spectre v2.
+ *
+ * This one sucks. A CPU is either:
+ *
+ * - Mitigated in hardware and advertised by ID_AA64PFR0_EL1.CSV2.
+ * - Mitigated in hardware and listed in our "safe list".
+ * - Mitigated in software by firmware.
+ * - Mitigated in software by a CPU-specific dance in the kernel.
+ * - Vulnerable.
+ *
+ * It's not unlikely for different CPUs in a big.LITTLE system to fall into
+ * different camps.
+ */
+static enum mitigation_state spectre_v2_state;
+
+static bool __read_mostly __nospectre_v2;
+static int __init parse_spectre_v2_param(char *str)
+{
+	__nospectre_v2 = true;
+	return 0;
+}
+early_param("nospectre_v2", parse_spectre_v2_param);
+
+static bool spectre_v2_mitigations_off(void)
+{
+	bool ret = __nospectre_v2 || cpu_mitigations_off();
+
+	if (ret)
+		pr_info_once("spectre-v2 mitigation disabled by command line option\n");
+
+	return ret;
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	switch (spectre_v2_state) {
+	case SPECTRE_UNAFFECTED:
+		return sprintf(buf, "Not affected\n");
+	case SPECTRE_MITIGATED:
+		return sprintf(buf, "Mitigation: Branch predictor hardening\n");
+	case SPECTRE_VULNERABLE:
+		fallthrough;
+	default:
+		return sprintf(buf, "Vulnerable\n");
+	}
+}
+
+static enum mitigation_state spectre_v2_get_cpu_hw_mitigation_state(void)
+{
+	u64 pfr0;
+	static const struct midr_range spectre_v2_safe_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+		MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
+		{ /* sentinel */ }
+	};
+
+	/* If the CPU has CSV2 set, we're safe */
+	pfr0 = read_cpuid(ID_AA64PFR0_EL1);
+	if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_CSV2_SHIFT))
+		return SPECTRE_UNAFFECTED;
+
+	/* Alternatively, we have a list of unaffected CPUs */
+	if (is_midr_in_range_list(read_cpuid_id(), spectre_v2_safe_list))
+		return SPECTRE_UNAFFECTED;
+
+	return SPECTRE_VULNERABLE;
+}
+
+#define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED	(1)
+
+static enum mitigation_state spectre_v2_get_cpu_fw_mitigation_state(void)
+{
+	int ret;
+	struct arm_smccc_res res;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+			     ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+
+	ret = res.a0;
+	switch (ret) {
+	case SMCCC_RET_SUCCESS:
+		return SPECTRE_MITIGATED;
+	case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED:
+		return SPECTRE_UNAFFECTED;
+	default:
+		fallthrough;
+	case SMCCC_RET_NOT_SUPPORTED:
+		return SPECTRE_VULNERABLE;
+	}
+}
+
+bool has_spectre_v2(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+
+	if (spectre_v2_get_cpu_hw_mitigation_state() == SPECTRE_UNAFFECTED)
+		return false;
+
+	if (spectre_v2_get_cpu_fw_mitigation_state() == SPECTRE_UNAFFECTED)
+		return false;
+
+	return true;
+}
+
+DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
+
+enum mitigation_state arm64_get_spectre_v2_state(void)
+{
+	return spectre_v2_state;
+}
+
+#ifdef CONFIG_KVM
+#include <asm/cacheflush.h>
+#include <asm/kvm_asm.h>
+
+atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
+
+static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
+				const char *hyp_vecs_end)
+{
+	void *dst = lm_alias(__bp_harden_hyp_vecs + slot * SZ_2K);
+	int i;
+
+	for (i = 0; i < SZ_2K; i += 0x80)
+		memcpy(dst + i, hyp_vecs_start, hyp_vecs_end - hyp_vecs_start);
+
+	__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
+}
+
+static void install_bp_hardening_cb(bp_hardening_cb_t fn)
+{
+	static DEFINE_RAW_SPINLOCK(bp_lock);
+	int cpu, slot = -1;
+	const char *hyp_vecs_start = __smccc_workaround_1_smc;
+	const char *hyp_vecs_end = __smccc_workaround_1_smc +
+				   __SMCCC_WORKAROUND_1_SMC_SZ;
+
+	/*
+	 * detect_harden_bp_fw() passes NULL for the hyp_vecs start/end if
+	 * we're a guest. Skip the hyp-vectors work.
+	 */
+	if (!is_hyp_mode_available()) {
+		__this_cpu_write(bp_hardening_data.fn, fn);
+		return;
+	}
+
+	raw_spin_lock(&bp_lock);
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(bp_hardening_data.fn, cpu) == fn) {
+			slot = per_cpu(bp_hardening_data.hyp_vectors_slot, cpu);
+			break;
+		}
+	}
+
+	if (slot == -1) {
+		slot = atomic_inc_return(&arm64_el2_vector_last_slot);
+		BUG_ON(slot >= BP_HARDEN_EL2_SLOTS);
+		__copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end);
+	}
+
+	__this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot);
+	__this_cpu_write(bp_hardening_data.fn, fn);
+	raw_spin_unlock(&bp_lock);
+}
+#else
+static void install_bp_hardening_cb(bp_hardening_cb_t fn)
+{
+	__this_cpu_write(bp_hardening_data.fn, fn);
+}
+#endif	/* CONFIG_KVM */
+
+static void call_smc_arch_workaround_1(void)
+{
+	arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
+}
+
+static void call_hvc_arch_workaround_1(void)
+{
+	arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
+}
+
+static void qcom_link_stack_sanitisation(void)
+{
+	u64 tmp;
+
+	asm volatile("mov	%0, x30		\n"
+		     ".rept	16		\n"
+		     "bl	. + 4		\n"
+		     ".endr			\n"
+		     "mov	x30, %0		\n"
+		     : "=&r" (tmp));
+}
+
+static enum mitigation_state spectre_v2_enable_fw_mitigation(void)
+{
+	bp_hardening_cb_t cb;
+	enum mitigation_state state;
+
+	state = spectre_v2_get_cpu_fw_mitigation_state();
+	if (state != SPECTRE_MITIGATED)
+		return state;
+
+	if (spectre_v2_mitigations_off())
+		return SPECTRE_VULNERABLE;
+
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
+		cb = call_hvc_arch_workaround_1;
+		break;
+
+	case SMCCC_CONDUIT_SMC:
+		cb = call_smc_arch_workaround_1;
+		break;
+
+	default:
+		return SPECTRE_VULNERABLE;
+	}
+
+	install_bp_hardening_cb(cb);
+	return SPECTRE_MITIGATED;
+}
+
+static enum mitigation_state spectre_v2_enable_sw_mitigation(void)
+{
+	u32 midr;
+
+	if (spectre_v2_mitigations_off())
+		return SPECTRE_VULNERABLE;
+
+	midr = read_cpuid_id();
+	if (((midr & MIDR_CPU_MODEL_MASK) != MIDR_QCOM_FALKOR) &&
+	    ((midr & MIDR_CPU_MODEL_MASK) != MIDR_QCOM_FALKOR_V1))
+		return SPECTRE_VULNERABLE;
+
+	install_bp_hardening_cb(qcom_link_stack_sanitisation);
+	return SPECTRE_MITIGATED;
+}
+
+void spectre_v2_enable_mitigation(const struct arm64_cpu_capabilities *__unused)
+{
+	enum mitigation_state state;
+
+	WARN_ON(preemptible());
+
+	state = spectre_v2_get_cpu_hw_mitigation_state();
+	if (state == SPECTRE_VULNERABLE)
+		state = spectre_v2_enable_fw_mitigation();
+	if (state == SPECTRE_VULNERABLE)
+		state = spectre_v2_enable_sw_mitigation();
+
+	update_mitigation_state(&spectre_v2_state, state);
+}
+
+/*
+ * Spectre v4.
+ *
+ * If you thought Spectre v2 was nasty, wait until you see this mess. A CPU is
+ * either:
+ *
+ * - Mitigated in hardware and listed in our "safe list".
+ * - Mitigated in hardware via PSTATE.SSBS.
+ * - Mitigated in software by firmware (sometimes referred to as SSBD).
+ *
+ * Wait, that doesn't sound so bad, does it? Keep reading...
+ *
+ * A major source of headaches is that the software mitigation is enabled both
+ * on a per-task basis, but can also be forced on for the kernel, necessitating
+ * both context-switch *and* entry/exit hooks. To make it even worse, some CPUs
+ * allow EL0 to toggle SSBS directly, which can end up with the prctl() state
+ * being stale when re-entering the kernel. The usual big.LITTLE caveats apply,
+ * so you can have systems that have both firmware and SSBS mitigations. This
+ * means we actually have to reject late onlining of CPUs with mitigations if
+ * all of the currently onlined CPUs are safelisted, as the mitigation tends to
+ * be opt-in for userspace. Yes, really, the cure is worse than the disease.
+ *
+ * The only good part is that if the firmware mitigation is present, then it is
+ * present for all CPUs, meaning we don't have to worry about late onlining of a
+ * vulnerable CPU if one of the boot CPUs is using the firmware mitigation.
+ *
+ * Give me a VAX-11/780 any day of the week...
+ */
+static enum mitigation_state spectre_v4_state;
+
+/* This is the per-cpu state tracking whether we need to talk to firmware */
+DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);
+
+enum spectre_v4_policy {
+	SPECTRE_V4_POLICY_MITIGATION_DYNAMIC,
+	SPECTRE_V4_POLICY_MITIGATION_ENABLED,
+	SPECTRE_V4_POLICY_MITIGATION_DISABLED,
+};
+
+static enum spectre_v4_policy __read_mostly __spectre_v4_policy;
+
+static const struct spectre_v4_param {
+	const char		*str;
+	enum spectre_v4_policy	policy;
+} spectre_v4_params[] = {
+	{ "force-on",	SPECTRE_V4_POLICY_MITIGATION_ENABLED, },
+	{ "force-off",	SPECTRE_V4_POLICY_MITIGATION_DISABLED, },
+	{ "kernel",	SPECTRE_V4_POLICY_MITIGATION_DYNAMIC, },
+};
+static int __init parse_spectre_v4_param(char *str)
+{
+	int i;
+
+	if (!str || !str[0])
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(spectre_v4_params); i++) {
+		const struct spectre_v4_param *param = &spectre_v4_params[i];
+
+		if (strncmp(str, param->str, strlen(param->str)))
+			continue;
+
+		__spectre_v4_policy = param->policy;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+early_param("ssbd", parse_spectre_v4_param);
+
+/*
+ * Because this was all written in a rush by people working in different silos,
+ * we've ended up with multiple command line options to control the same thing.
+ * Wrap these up in some helpers, which prefer disabling the mitigation if faced
+ * with contradictory parameters. The mitigation is always either "off",
+ * "dynamic" or "on".
+ */
+static bool spectre_v4_mitigations_off(void)
+{
+	bool ret = cpu_mitigations_off() ||
+		   __spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_DISABLED;
+
+	if (ret)
+		pr_info_once("spectre-v4 mitigation disabled by command-line option\n");
+
+	return ret;
+}
+
+/* Do we need to toggle the mitigation state on entry to/exit from the kernel? */
+static bool spectre_v4_mitigations_dynamic(void)
+{
+	return !spectre_v4_mitigations_off() &&
+	       __spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_DYNAMIC;
+}
+
+static bool spectre_v4_mitigations_on(void)
+{
+	return !spectre_v4_mitigations_off() &&
+	       __spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_ENABLED;
+}
+
+ssize_t cpu_show_spec_store_bypass(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	switch (spectre_v4_state) {
+	case SPECTRE_UNAFFECTED:
+		return sprintf(buf, "Not affected\n");
+	case SPECTRE_MITIGATED:
+		return sprintf(buf, "Mitigation: Speculative Store Bypass disabled via prctl\n");
+	case SPECTRE_VULNERABLE:
+		fallthrough;
+	default:
+		return sprintf(buf, "Vulnerable\n");
+	}
+}
+
+enum mitigation_state arm64_get_spectre_v4_state(void)
+{
+	return spectre_v4_state;
+}
+
+static enum mitigation_state spectre_v4_get_cpu_hw_mitigation_state(void)
+{
+	static const struct midr_range spectre_v4_safe_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+		MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
+		{ /* sentinel */ },
+	};
+
+	if (is_midr_in_range_list(read_cpuid_id(), spectre_v4_safe_list))
+		return SPECTRE_UNAFFECTED;
+
+	/* CPU features are detected first */
+	if (this_cpu_has_cap(ARM64_SSBS))
+		return SPECTRE_MITIGATED;
+
+	return SPECTRE_VULNERABLE;
+}
+
+static enum mitigation_state spectre_v4_get_cpu_fw_mitigation_state(void)
+{
+	int ret;
+	struct arm_smccc_res res;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+			     ARM_SMCCC_ARCH_WORKAROUND_2, &res);
+
+	ret = res.a0;
+	switch (ret) {
+	case SMCCC_RET_SUCCESS:
+		return SPECTRE_MITIGATED;
+	case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED:
+		fallthrough;
+	case SMCCC_RET_NOT_REQUIRED:
+		return SPECTRE_UNAFFECTED;
+	default:
+		fallthrough;
+	case SMCCC_RET_NOT_SUPPORTED:
+		return SPECTRE_VULNERABLE;
+	}
+}
+
+bool has_spectre_v4(const struct arm64_cpu_capabilities *cap, int scope)
+{
+	enum mitigation_state state;
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+
+	state = spectre_v4_get_cpu_hw_mitigation_state();
+	if (state == SPECTRE_VULNERABLE)
+		state = spectre_v4_get_cpu_fw_mitigation_state();
+
+	return state != SPECTRE_UNAFFECTED;
+}
+
+static int ssbs_emulation_handler(struct pt_regs *regs, u32 instr)
+{
+	if (user_mode(regs))
+		return 1;
+
+	if (instr & BIT(PSTATE_Imm_shift))
+		regs->pstate |= PSR_SSBS_BIT;
+	else
+		regs->pstate &= ~PSR_SSBS_BIT;
+
+	arm64_skip_faulting_instruction(regs, 4);
+	return 0;
+}
+
+static struct undef_hook ssbs_emulation_hook = {
+	.instr_mask	= ~(1U << PSTATE_Imm_shift),
+	.instr_val	= 0xd500401f | PSTATE_SSBS,
+	.fn		= ssbs_emulation_handler,
+};
+
+static enum mitigation_state spectre_v4_enable_hw_mitigation(void)
+{
+	static bool undef_hook_registered = false;
+	static DEFINE_RAW_SPINLOCK(hook_lock);
+	enum mitigation_state state;
+
+	/*
+	 * If the system is mitigated but this CPU doesn't have SSBS, then
+	 * we must be on the safelist and there's nothing more to do.
+	 */
+	state = spectre_v4_get_cpu_hw_mitigation_state();
+	if (state != SPECTRE_MITIGATED || !this_cpu_has_cap(ARM64_SSBS))
+		return state;
+
+	raw_spin_lock(&hook_lock);
+	if (!undef_hook_registered) {
+		register_undef_hook(&ssbs_emulation_hook);
+		undef_hook_registered = true;
+	}
+	raw_spin_unlock(&hook_lock);
+
+	if (spectre_v4_mitigations_off()) {
+		sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS);
+		asm volatile(SET_PSTATE_SSBS(1));
+		return SPECTRE_VULNERABLE;
+	}
+
+	/* SCTLR_EL1.DSSBS was initialised to 0 during boot */
+	asm volatile(SET_PSTATE_SSBS(0));
+	return SPECTRE_MITIGATED;
+}
+
+/*
+ * Patch a branch over the Spectre-v4 mitigation code with a NOP so that
+ * we fallthrough and check whether firmware needs to be called on this CPU.
+ */
+void __init spectre_v4_patch_fw_mitigation_enable(struct alt_instr *alt,
+						  __le32 *origptr,
+						  __le32 *updptr, int nr_inst)
+{
+	BUG_ON(nr_inst != 1); /* Branch -> NOP */
+
+	if (spectre_v4_mitigations_off())
+		return;
+
+	if (cpus_have_final_cap(ARM64_SSBS))
+		return;
+
+	if (spectre_v4_mitigations_dynamic())
+		*updptr = cpu_to_le32(aarch64_insn_gen_nop());
+}
+
+/*
+ * Patch a NOP in the Spectre-v4 mitigation code with an SMC/HVC instruction
+ * to call into firmware to adjust the mitigation state.
+ */
+void __init spectre_v4_patch_fw_mitigation_conduit(struct alt_instr *alt,
+						   __le32 *origptr,
+						   __le32 *updptr, int nr_inst)
+{
+	u32 insn;
+
+	BUG_ON(nr_inst != 1); /* NOP -> HVC/SMC */
+
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
+		insn = aarch64_insn_get_hvc_value();
+		break;
+	case SMCCC_CONDUIT_SMC:
+		insn = aarch64_insn_get_smc_value();
+		break;
+	default:
+		return;
+	}
+
+	*updptr = cpu_to_le32(insn);
+}
+
+static enum mitigation_state spectre_v4_enable_fw_mitigation(void)
+{
+	enum mitigation_state state;
+
+	state = spectre_v4_get_cpu_fw_mitigation_state();
+	if (state != SPECTRE_MITIGATED)
+		return state;
+
+	if (spectre_v4_mitigations_off()) {
+		arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, false, NULL);
+		return SPECTRE_VULNERABLE;
+	}
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, true, NULL);
+
+	if (spectre_v4_mitigations_dynamic())
+		__this_cpu_write(arm64_ssbd_callback_required, 1);
+
+	return SPECTRE_MITIGATED;
+}
+
+void spectre_v4_enable_mitigation(const struct arm64_cpu_capabilities *__unused)
+{
+	enum mitigation_state state;
+
+	WARN_ON(preemptible());
+
+	state = spectre_v4_enable_hw_mitigation();
+	if (state == SPECTRE_VULNERABLE)
+		state = spectre_v4_enable_fw_mitigation();
+
+	update_mitigation_state(&spectre_v4_state, state);
+}
+
+static void __update_pstate_ssbs(struct pt_regs *regs, bool state)
+{
+	u64 bit = compat_user_mode(regs) ? PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
+
+	if (state)
+		regs->pstate |= bit;
+	else
+		regs->pstate &= ~bit;
+}
+
+void spectre_v4_enable_task_mitigation(struct task_struct *tsk)
+{
+	struct pt_regs *regs = task_pt_regs(tsk);
+	bool ssbs = false, kthread = tsk->flags & PF_KTHREAD;
+
+	if (spectre_v4_mitigations_off())
+		ssbs = true;
+	else if (spectre_v4_mitigations_dynamic() && !kthread)
+		ssbs = !test_tsk_thread_flag(tsk, TIF_SSBD);
+
+	__update_pstate_ssbs(regs, ssbs);
+}
+
+/*
+ * The Spectre-v4 mitigation can be controlled via a prctl() from userspace.
+ * This is interesting because the "speculation disabled" behaviour can be
+ * configured so that it is preserved across exec(), which means that the
+ * prctl() may be necessary even when PSTATE.SSBS can be toggled directly
+ * from userspace.
+ */
+static void ssbd_prctl_enable_mitigation(struct task_struct *task)
+{
+	task_clear_spec_ssb_noexec(task);
+	task_set_spec_ssb_disable(task);
+	set_tsk_thread_flag(task, TIF_SSBD);
+}
+
+static void ssbd_prctl_disable_mitigation(struct task_struct *task)
+{
+	task_clear_spec_ssb_noexec(task);
+	task_clear_spec_ssb_disable(task);
+	clear_tsk_thread_flag(task, TIF_SSBD);
+}
+
+static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
+	switch (ctrl) {
+	case PR_SPEC_ENABLE:
+		/* Enable speculation: disable mitigation */
+		/*
+		 * Force disabled speculation prevents it from being
+		 * re-enabled.
+		 */
+		if (task_spec_ssb_force_disable(task))
+			return -EPERM;
+
+		/*
+		 * If the mitigation is forced on, then speculation is forced
+		 * off and we again prevent it from being re-enabled.
+		 */
+		if (spectre_v4_mitigations_on())
+			return -EPERM;
+
+		ssbd_prctl_disable_mitigation(task);
+		break;
+	case PR_SPEC_FORCE_DISABLE:
+		/* Force disable speculation: force enable mitigation */
+		/*
+		 * If the mitigation is forced off, then speculation is forced
+		 * on and we prevent it from being disabled.
+		 */
+		if (spectre_v4_mitigations_off())
+			return -EPERM;
+
+		task_set_spec_ssb_force_disable(task);
+		fallthrough;
+	case PR_SPEC_DISABLE:
+		/* Disable speculation: enable mitigation */
+		/* Same as PR_SPEC_FORCE_DISABLE */
+		if (spectre_v4_mitigations_off())
+			return -EPERM;
+
+		ssbd_prctl_enable_mitigation(task);
+		break;
+	case PR_SPEC_DISABLE_NOEXEC:
+		/* Disable speculation until execve(): enable mitigation */
+		/*
+		 * If the mitigation state is forced one way or the other, then
+		 * we must fail now before we try to toggle it on execve().
+		 */
+		if (task_spec_ssb_force_disable(task) ||
+		    spectre_v4_mitigations_off() ||
+		    spectre_v4_mitigations_on()) {
+			return -EPERM;
+		}
+
+		ssbd_prctl_enable_mitigation(task);
+		task_set_spec_ssb_noexec(task);
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	spectre_v4_enable_task_mitigation(task);
+	return 0;
+}
+
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+			     unsigned long ctrl)
+{
+	switch (which) {
+	case PR_SPEC_STORE_BYPASS:
+		return ssbd_prctl_set(task, ctrl);
+	default:
+		return -ENODEV;
+	}
+}
+
+static int ssbd_prctl_get(struct task_struct *task)
+{
+	switch (spectre_v4_state) {
+	case SPECTRE_UNAFFECTED:
+		return PR_SPEC_NOT_AFFECTED;
+	case SPECTRE_MITIGATED:
+		if (spectre_v4_mitigations_on())
+			return PR_SPEC_NOT_AFFECTED;
+
+		if (spectre_v4_mitigations_dynamic())
+			break;
+
+		/* Mitigations are disabled, so we're vulnerable. */
+		fallthrough;
+	case SPECTRE_VULNERABLE:
+		fallthrough;
+	default:
+		return PR_SPEC_ENABLE;
+	}
+
+	/* Check the mitigation state for this task */
+	if (task_spec_ssb_force_disable(task))
+		return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+
+	if (task_spec_ssb_noexec(task))
+		return PR_SPEC_PRCTL | PR_SPEC_DISABLE_NOEXEC;
+
+	if (task_spec_ssb_disable(task))
+		return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+
+	return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+}
+
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
+{
+	switch (which) {
+	case PR_SPEC_STORE_BYPASS:
+		return ssbd_prctl_get(task);
+	default:
+		return -ENODEV;
+	}
+}
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index d8ebfd8..f49b349 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -34,6 +34,7 @@
 #include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/fpsimd.h>
+#include <asm/mte.h>
 #include <asm/pointer_auth.h>
 #include <asm/stacktrace.h>
 #include <asm/syscall.h>
@@ -1032,6 +1033,35 @@
 #endif /* CONFIG_CHECKPOINT_RESTORE */
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+static int tagged_addr_ctrl_get(struct task_struct *target,
+				const struct user_regset *regset,
+				struct membuf to)
+{
+	long ctrl = get_tagged_addr_ctrl(target);
+
+	if (IS_ERR_VALUE(ctrl))
+		return ctrl;
+
+	return membuf_write(&to, &ctrl, sizeof(ctrl));
+}
+
+static int tagged_addr_ctrl_set(struct task_struct *target, const struct
+				user_regset *regset, unsigned int pos,
+				unsigned int count, const void *kbuf, const
+				void __user *ubuf)
+{
+	int ret;
+	long ctrl;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1);
+	if (ret)
+		return ret;
+
+	return set_tagged_addr_ctrl(target, ctrl);
+}
+#endif
+
 enum aarch64_regset {
 	REGSET_GPR,
 	REGSET_FPR,
@@ -1051,6 +1081,9 @@
 	REGSET_PACG_KEYS,
 #endif
 #endif
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+	REGSET_TAGGED_ADDR_CTRL,
+#endif
 };
 
 static const struct user_regset aarch64_regsets[] = {
@@ -1148,6 +1181,16 @@
 	},
 #endif
 #endif
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+	[REGSET_TAGGED_ADDR_CTRL] = {
+		.core_note_type = NT_ARM_TAGGED_ADDR_CTRL,
+		.n = 1,
+		.size = sizeof(long),
+		.align = sizeof(long),
+		.regset_get = tagged_addr_ctrl_get,
+		.set = tagged_addr_ctrl_set,
+	},
+#endif
 };
 
 static const struct user_regset_view user_aarch64_view = {
@@ -1691,6 +1734,12 @@
 long arch_ptrace(struct task_struct *child, long request,
 		 unsigned long addr, unsigned long data)
 {
+	switch (request) {
+	case PTRACE_PEEKMTETAGS:
+	case PTRACE_POKEMTETAGS:
+		return mte_ptrace_copy_tags(child, request, addr, data);
+	}
+
 	return ptrace_request(child, request, addr, data);
 }
 
@@ -1793,7 +1842,7 @@
  * We also reserve IL for the kernel; SS is handled dynamically.
  */
 #define SPSR_EL1_AARCH64_RES0_BITS \
-	(GENMASK_ULL(63, 32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
+	(GENMASK_ULL(63, 32) | GENMASK_ULL(27, 26) | GENMASK_ULL(23, 22) | \
 	 GENMASK_ULL(20, 13) | GENMASK_ULL(5, 5))
 #define SPSR_EL1_AARCH32_RES0_BITS \
 	(GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20))
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index 542d6ed..84eec95 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -36,18 +36,6 @@
 	mov	x14, xzr			/* x14 = entry ptr */
 	mov	x13, xzr			/* x13 = copy dest */
 
-	/* Clear the sctlr_el2 flags. */
-	mrs	x0, CurrentEL
-	cmp	x0, #CurrentEL_EL2
-	b.ne	1f
-	mrs	x0, sctlr_el2
-	mov_q	x1, SCTLR_ELx_FLAGS
-	bic	x0, x0, x1
-	pre_disable_mmu_workaround
-	msr	sctlr_el2, x0
-	isb
-1:
-
 	/* Check if the new image needs relocation. */
 	tbnz	x16, IND_DONE_BIT, .Ldone
 
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
index a5e8b3b..a6d18755 100644
--- a/arch/arm64/kernel/return_address.c
+++ b/arch/arm64/kernel/return_address.c
@@ -18,16 +18,16 @@
 	void *addr;
 };
 
-static int save_return_addr(struct stackframe *frame, void *d)
+static bool save_return_addr(void *d, unsigned long pc)
 {
 	struct return_address_data *data = d;
 
 	if (!data->level) {
-		data->addr = (void *)frame->pc;
-		return 1;
+		data->addr = (void *)pc;
+		return false;
 	} else {
 		--data->level;
-		return 0;
+		return true;
 	}
 }
 NOKPROBE_SYMBOL(save_return_addr);
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 77c4c9b..53acbec 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -280,7 +280,6 @@
 {
 	return __cpu_logical_map[cpu];
 }
-EXPORT_SYMBOL_GPL(cpu_logical_map);
 
 void __init __no_sanitize_address setup_arch(char **cmdline_p)
 {
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 3b4f31f..bdcaaf0 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -244,7 +244,8 @@
 	if (vq) {
 		/*
 		 * This assumes that the SVE state has already been saved to
-		 * the task struct by calling preserve_fpsimd_context().
+		 * the task struct by calling the function
+		 * fpsimd_signal_preserve_current_state().
 		 */
 		err |= __copy_to_user((char __user *)ctx + SVE_SIG_REGS_OFFSET,
 				      current->thread.sve_state,
@@ -748,6 +749,9 @@
 		regs->pstate |= PSR_BTYPE_C;
 	}
 
+	/* TCO (Tag Check Override) always cleared for signal handlers */
+	regs->pstate &= ~PSR_TCO_BIT;
+
 	if (ka->sa.sa_flags & SA_RESTORER)
 		sigtramp = ka->sa.sa_restorer;
 	else
@@ -932,6 +936,12 @@
 			if (thread_flags & _TIF_UPROBE)
 				uprobe_notify_resume(regs);
 
+			if (thread_flags & _TIF_MTE_ASYNC_FAULT) {
+				clear_thread_flag(TIF_MTE_ASYNC_FAULT);
+				send_sig_fault(SIGSEGV, SEGV_MTEAERR,
+					       (void __user *)NULL, current);
+			}
+
 			if (thread_flags & _TIF_SIGPENDING)
 				do_signal(regs);
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 03957a1..355ee9e 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -151,7 +151,7 @@
 			break;
 		}
 		pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
-		/* Fall through */
+		fallthrough;
 	case CPU_STUCK_IN_KERNEL:
 		pr_crit("CPU%u: is stuck in kernel\n", cpu);
 		if (status & CPU_STUCK_REASON_52_BIT_VA)
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index c8a3fee..5892e79 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -83,9 +83,9 @@
 
 	/*
 	 * We write the release address as LE regardless of the native
-	 * endianess of the kernel. Therefore, any boot-loaders that
+	 * endianness of the kernel. Therefore, any boot-loaders that
 	 * read this address need to convert this address to the
-	 * boot-loader's endianess before jumping. This is mandated by
+	 * boot-loader's endianness before jumping. This is mandated by
 	 * the boot protocol.
 	 */
 	writeq_relaxed(__pa_symbol(secondary_holding_pen), release_addr);
diff --git a/arch/arm64/kernel/ssbd.c b/arch/arm64/kernel/ssbd.c
deleted file mode 100644
index b26955f..0000000
--- a/arch/arm64/kernel/ssbd.c
+++ /dev/null
@@ -1,129 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2018 ARM Ltd, All Rights Reserved.
- */
-
-#include <linux/compat.h>
-#include <linux/errno.h>
-#include <linux/prctl.h>
-#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
-#include <linux/thread_info.h>
-
-#include <asm/cpufeature.h>
-
-static void ssbd_ssbs_enable(struct task_struct *task)
-{
-	u64 val = is_compat_thread(task_thread_info(task)) ?
-		  PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
-
-	task_pt_regs(task)->pstate |= val;
-}
-
-static void ssbd_ssbs_disable(struct task_struct *task)
-{
-	u64 val = is_compat_thread(task_thread_info(task)) ?
-		  PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
-
-	task_pt_regs(task)->pstate &= ~val;
-}
-
-/*
- * prctl interface for SSBD
- */
-static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
-{
-	int state = arm64_get_ssbd_state();
-
-	/* Unsupported */
-	if (state == ARM64_SSBD_UNKNOWN)
-		return -ENODEV;
-
-	/* Treat the unaffected/mitigated state separately */
-	if (state == ARM64_SSBD_MITIGATED) {
-		switch (ctrl) {
-		case PR_SPEC_ENABLE:
-			return -EPERM;
-		case PR_SPEC_DISABLE:
-		case PR_SPEC_FORCE_DISABLE:
-			return 0;
-		}
-	}
-
-	/*
-	 * Things are a bit backward here: the arm64 internal API
-	 * *enables the mitigation* when the userspace API *disables
-	 * speculation*. So much fun.
-	 */
-	switch (ctrl) {
-	case PR_SPEC_ENABLE:
-		/* If speculation is force disabled, enable is not allowed */
-		if (state == ARM64_SSBD_FORCE_ENABLE ||
-		    task_spec_ssb_force_disable(task))
-			return -EPERM;
-		task_clear_spec_ssb_disable(task);
-		clear_tsk_thread_flag(task, TIF_SSBD);
-		ssbd_ssbs_enable(task);
-		break;
-	case PR_SPEC_DISABLE:
-		if (state == ARM64_SSBD_FORCE_DISABLE)
-			return -EPERM;
-		task_set_spec_ssb_disable(task);
-		set_tsk_thread_flag(task, TIF_SSBD);
-		ssbd_ssbs_disable(task);
-		break;
-	case PR_SPEC_FORCE_DISABLE:
-		if (state == ARM64_SSBD_FORCE_DISABLE)
-			return -EPERM;
-		task_set_spec_ssb_disable(task);
-		task_set_spec_ssb_force_disable(task);
-		set_tsk_thread_flag(task, TIF_SSBD);
-		ssbd_ssbs_disable(task);
-		break;
-	default:
-		return -ERANGE;
-	}
-
-	return 0;
-}
-
-int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
-			     unsigned long ctrl)
-{
-	switch (which) {
-	case PR_SPEC_STORE_BYPASS:
-		return ssbd_prctl_set(task, ctrl);
-	default:
-		return -ENODEV;
-	}
-}
-
-static int ssbd_prctl_get(struct task_struct *task)
-{
-	switch (arm64_get_ssbd_state()) {
-	case ARM64_SSBD_UNKNOWN:
-		return -ENODEV;
-	case ARM64_SSBD_FORCE_ENABLE:
-		return PR_SPEC_DISABLE;
-	case ARM64_SSBD_KERNEL:
-		if (task_spec_ssb_force_disable(task))
-			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
-		if (task_spec_ssb_disable(task))
-			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
-		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
-	case ARM64_SSBD_FORCE_DISABLE:
-		return PR_SPEC_ENABLE;
-	default:
-		return PR_SPEC_NOT_AFFECTED;
-	}
-}
-
-int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
-{
-	switch (which) {
-	case PR_SPEC_STORE_BYPASS:
-		return ssbd_prctl_get(task);
-	default:
-		return -ENODEV;
-	}
-}
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 2dd8e3b..fa56af1 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -118,12 +118,12 @@
 NOKPROBE_SYMBOL(unwind_frame);
 
 void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
-		     int (*fn)(struct stackframe *, void *), void *data)
+			     bool (*fn)(void *, unsigned long), void *data)
 {
 	while (1) {
 		int ret;
 
-		if (fn(frame, data))
+		if (!fn(data, frame->pc))
 			break;
 		ret = unwind_frame(tsk, frame);
 		if (ret < 0)
@@ -132,84 +132,89 @@
 }
 NOKPROBE_SYMBOL(walk_stackframe);
 
-#ifdef CONFIG_STACKTRACE
-struct stack_trace_data {
-	struct stack_trace *trace;
-	unsigned int no_sched_functions;
-	unsigned int skip;
-};
-
-static int save_trace(struct stackframe *frame, void *d)
+static void dump_backtrace_entry(unsigned long where, const char *loglvl)
 {
-	struct stack_trace_data *data = d;
-	struct stack_trace *trace = data->trace;
-	unsigned long addr = frame->pc;
+	printk("%s %pS\n", loglvl, (void *)where);
+}
 
-	if (data->no_sched_functions && in_sched_functions(addr))
-		return 0;
-	if (data->skip) {
-		data->skip--;
-		return 0;
+void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
+		    const char *loglvl)
+{
+	struct stackframe frame;
+	int skip = 0;
+
+	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
+
+	if (regs) {
+		if (user_mode(regs))
+			return;
+		skip = 1;
 	}
 
-	trace->entries[trace->nr_entries++] = addr;
-
-	return trace->nr_entries >= trace->max_entries;
-}
-
-void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
-{
-	struct stack_trace_data data;
-	struct stackframe frame;
-
-	data.trace = trace;
-	data.skip = trace->skip;
-	data.no_sched_functions = 0;
-
-	start_backtrace(&frame, regs->regs[29], regs->pc);
-	walk_stackframe(current, &frame, save_trace, &data);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace_regs);
-
-static noinline void __save_stack_trace(struct task_struct *tsk,
-	struct stack_trace *trace, unsigned int nosched)
-{
-	struct stack_trace_data data;
-	struct stackframe frame;
+	if (!tsk)
+		tsk = current;
 
 	if (!try_get_task_stack(tsk))
 		return;
 
-	data.trace = trace;
-	data.skip = trace->skip;
-	data.no_sched_functions = nosched;
-
-	if (tsk != current) {
-		start_backtrace(&frame, thread_saved_fp(tsk),
-				thread_saved_pc(tsk));
-	} else {
-		/* We don't want this function nor the caller */
-		data.skip += 2;
+	if (tsk == current) {
 		start_backtrace(&frame,
 				(unsigned long)__builtin_frame_address(0),
-				(unsigned long)__save_stack_trace);
+				(unsigned long)dump_backtrace);
+	} else {
+		/*
+		 * task blocked in __switch_to
+		 */
+		start_backtrace(&frame,
+				thread_saved_fp(tsk),
+				thread_saved_pc(tsk));
 	}
 
-	walk_stackframe(tsk, &frame, save_trace, &data);
+	printk("%sCall trace:\n", loglvl);
+	do {
+		/* skip until specified stack frame */
+		if (!skip) {
+			dump_backtrace_entry(frame.pc, loglvl);
+		} else if (frame.fp == regs->regs[29]) {
+			skip = 0;
+			/*
+			 * Mostly, this is the case where this function is
+			 * called in panic/abort. As exception handler's
+			 * stack frame does not contain the corresponding pc
+			 * at which an exception has taken place, use regs->pc
+			 * instead.
+			 */
+			dump_backtrace_entry(regs->pc, loglvl);
+		}
+	} while (!unwind_frame(tsk, &frame));
 
 	put_task_stack(tsk);
 }
 
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 {
-	__save_stack_trace(tsk, trace, 1);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
-
-void save_stack_trace(struct stack_trace *trace)
-{
-	__save_stack_trace(current, trace, 0);
+	dump_backtrace(NULL, tsk, loglvl);
+	barrier();
 }
 
-EXPORT_SYMBOL_GPL(save_stack_trace);
+#ifdef CONFIG_STACKTRACE
+
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+		     struct task_struct *task, struct pt_regs *regs)
+{
+	struct stackframe frame;
+
+	if (regs)
+		start_backtrace(&frame, regs->regs[29], regs->pc);
+	else if (task == current)
+		start_backtrace(&frame,
+				(unsigned long)__builtin_frame_address(0),
+				(unsigned long)arch_stack_walk);
+	else
+		start_backtrace(&frame, thread_saved_fp(task),
+				thread_saved_pc(task));
+
+	walk_stackframe(task, &frame, consume_entry, cookie);
+}
+
 #endif
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index c1dee90..96cd347 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -10,6 +10,7 @@
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/exec.h>
+#include <asm/mte.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
 #include <asm/smp_plat.h>
@@ -72,8 +73,10 @@
 	 * have turned the mitigation on. If the user has forcefully
 	 * disabled it, make sure their wishes are obeyed.
 	 */
-	if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
-		arm64_set_ssbd_mitigation(false);
+	spectre_v4_enable_mitigation(NULL);
+
+	/* Restore additional MTE-specific configuration */
+	mte_suspend_exit();
 }
 
 /*
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 5f0c048..e4c0dad 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -123,6 +123,16 @@
 	local_daif_restore(DAIF_PROCCTX);
 	user_exit();
 
+	if (system_supports_mte() && (flags & _TIF_MTE_ASYNC_FAULT)) {
+		/*
+		 * Process the asynchronous tag check fault before the actual
+		 * syscall. do_notify_resume() will send a signal to userspace
+		 * before the syscall is restarted.
+		 */
+		regs->regs[0] = -ERESTARTNOINTR;
+		return;
+	}
+
 	if (has_syscall_work(flags)) {
 		/*
 		 * The de-facto standard way to skip a system call using ptrace
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 0801a0f..ff1dd1d 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -36,21 +36,23 @@
 	if (mpidr & MPIDR_UP_BITMASK)
 		return;
 
-	/* Create cpu topology mapping based on MPIDR. */
-	if (mpidr & MPIDR_MT_BITMASK) {
-		/* Multiprocessor system : Multi-threads per core */
-		cpuid_topo->thread_id  = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-		cpuid_topo->core_id    = MPIDR_AFFINITY_LEVEL(mpidr, 1);
-		cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 2) |
-					 MPIDR_AFFINITY_LEVEL(mpidr, 3) << 8;
-	} else {
-		/* Multiprocessor system : Single-thread per core */
-		cpuid_topo->thread_id  = -1;
-		cpuid_topo->core_id    = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-		cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 1) |
-					 MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8 |
-					 MPIDR_AFFINITY_LEVEL(mpidr, 3) << 16;
-	}
+	/*
+	 * This would be the place to create cpu topology based on MPIDR.
+	 *
+	 * However, it cannot be trusted to depict the actual topology; some
+	 * pieces of the architecture enforce an artificial cap on Aff0 values
+	 * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an
+	 * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up
+	 * having absolutely no relationship to the actual underlying system
+	 * topology, and cannot be reasonably used as core / package ID.
+	 *
+	 * If the MT bit is set, Aff0 *could* be used to define a thread ID, but
+	 * we still wouldn't be able to obtain a sane core ID. This means we
+	 * need to entirely ignore MPIDR for any topology deduction.
+	 */
+	cpuid_topo->thread_id  = -1;
+	cpuid_topo->core_id    = cpuid;
+	cpuid_topo->package_id = cpu_to_node(cpuid);
 
 	pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n",
 		 cpuid, cpuid_topo->package_id, cpuid_topo->core_id,
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 13ebd5c..8af4e0e 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -34,6 +34,7 @@
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
+#include <asm/extable.h>
 #include <asm/insn.h>
 #include <asm/kprobes.h>
 #include <asm/traps.h>
@@ -53,11 +54,6 @@
 
 int show_unhandled_signals = 0;
 
-static void dump_backtrace_entry(unsigned long where, const char *loglvl)
-{
-	printk("%s %pS\n", loglvl, (void *)where);
-}
-
 static void dump_kernel_instr(const char *lvl, struct pt_regs *regs)
 {
 	unsigned long addr = instruction_pointer(regs);
@@ -83,66 +79,6 @@
 	printk("%sCode: %s\n", lvl, str);
 }
 
-void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
-		    const char *loglvl)
-{
-	struct stackframe frame;
-	int skip = 0;
-
-	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
-
-	if (regs) {
-		if (user_mode(regs))
-			return;
-		skip = 1;
-	}
-
-	if (!tsk)
-		tsk = current;
-
-	if (!try_get_task_stack(tsk))
-		return;
-
-	if (tsk == current) {
-		start_backtrace(&frame,
-				(unsigned long)__builtin_frame_address(0),
-				(unsigned long)dump_backtrace);
-	} else {
-		/*
-		 * task blocked in __switch_to
-		 */
-		start_backtrace(&frame,
-				thread_saved_fp(tsk),
-				thread_saved_pc(tsk));
-	}
-
-	printk("%sCall trace:\n", loglvl);
-	do {
-		/* skip until specified stack frame */
-		if (!skip) {
-			dump_backtrace_entry(frame.pc, loglvl);
-		} else if (frame.fp == regs->regs[29]) {
-			skip = 0;
-			/*
-			 * Mostly, this is the case where this function is
-			 * called in panic/abort. As exception handler's
-			 * stack frame does not contain the corresponding pc
-			 * at which an exception has taken place, use regs->pc
-			 * instead.
-			 */
-			dump_backtrace_entry(regs->pc, loglvl);
-		}
-	} while (!unwind_frame(tsk, &frame));
-
-	put_task_stack(tsk);
-}
-
-void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
-{
-	dump_backtrace(NULL, tsk, loglvl);
-	barrier();
-}
-
 #ifdef CONFIG_PREEMPT
 #define S_PREEMPT " PREEMPT"
 #elif defined(CONFIG_PREEMPT_RT)
@@ -200,9 +136,9 @@
 	oops_exit();
 
 	if (in_interrupt())
-		panic("Fatal exception in interrupt");
+		panic("%s: Fatal exception in interrupt", str);
 	if (panic_on_oops)
-		panic("Fatal exception");
+		panic("%s: Fatal exception", str);
 
 	raw_spin_unlock_irqrestore(&die_lock, flags);
 
@@ -412,7 +348,7 @@
 	return fn ? fn(regs, instr) : 1;
 }
 
-void force_signal_inject(int signal, int code, unsigned long address)
+void force_signal_inject(int signal, int code, unsigned long address, unsigned int err)
 {
 	const char *desc;
 	struct pt_regs *regs = current_pt_regs();
@@ -438,7 +374,7 @@
 		signal = SIGKILL;
 	}
 
-	arm64_notify_die(desc, regs, signal, code, (void __user *)address, 0);
+	arm64_notify_die(desc, regs, signal, code, (void __user *)address, err);
 }
 
 /*
@@ -455,7 +391,7 @@
 		code = SEGV_ACCERR;
 	mmap_read_unlock(current->mm);
 
-	force_signal_inject(SIGSEGV, code, addr);
+	force_signal_inject(SIGSEGV, code, addr, 0);
 }
 
 void do_undefinstr(struct pt_regs *regs)
@@ -468,17 +404,28 @@
 		return;
 
 	BUG_ON(!user_mode(regs));
-	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
+	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
 }
 NOKPROBE_SYMBOL(do_undefinstr);
 
 void do_bti(struct pt_regs *regs)
 {
 	BUG_ON(!user_mode(regs));
-	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
+	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
 }
 NOKPROBE_SYMBOL(do_bti);
 
+void do_ptrauth_fault(struct pt_regs *regs, unsigned int esr)
+{
+	/*
+	 * Unexpected FPAC exception or pointer authentication failure in
+	 * the kernel: kill the task before it does any more harm.
+	 */
+	BUG_ON(!user_mode(regs));
+	force_signal_inject(SIGILL, ILL_ILLOPN, regs->pc, esr);
+}
+NOKPROBE_SYMBOL(do_ptrauth_fault);
+
 #define __user_cache_maint(insn, address, res)			\
 	if (address >= user_addr_max()) {			\
 		res = -EFAULT;					\
@@ -528,7 +475,7 @@
 		__user_cache_maint("ic ivau", address, ret);
 		break;
 	default:
-		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
 		return;
 	}
 
@@ -581,7 +528,7 @@
 	sysreg = esr_sys64_to_sysreg(esr);
 
 	if (do_emulate_mrs(regs, sysreg, rt) != 0)
-		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
 }
 
 static void wfi_handler(unsigned int esr, struct pt_regs *regs)
@@ -775,6 +722,7 @@
 	[ESR_ELx_EC_SYS64]		= "MSR/MRS (AArch64)",
 	[ESR_ELx_EC_SVE]		= "SVE",
 	[ESR_ELx_EC_ERET]		= "ERET/ERETAA/ERETAB",
+	[ESR_ELx_EC_FPAC]		= "FPAC",
 	[ESR_ELx_EC_IMP_DEF]		= "EL3 IMP DEF",
 	[ESR_ELx_EC_IABT_LOW]		= "IABT (lower EL)",
 	[ESR_ELx_EC_IABT_CUR]		= "IABT (current EL)",
@@ -935,26 +883,6 @@
 }
 NOKPROBE_SYMBOL(enter_from_user_mode);
 
-void __pte_error(const char *file, int line, unsigned long val)
-{
-	pr_err("%s:%d: bad pte %016lx.\n", file, line, val);
-}
-
-void __pmd_error(const char *file, int line, unsigned long val)
-{
-	pr_err("%s:%d: bad pmd %016lx.\n", file, line, val);
-}
-
-void __pud_error(const char *file, int line, unsigned long val)
-{
-	pr_err("%s:%d: bad pud %016lx.\n", file, line, val);
-}
-
-void __pgd_error(const char *file, int line, unsigned long val)
-{
-	pr_err("%s:%d: bad pgd %016lx.\n", file, line, val);
-}
-
 /* GENERIC_BUG traps */
 
 int is_valid_bugaddr(unsigned long addr)
@@ -994,6 +922,21 @@
 	.imm = BUG_BRK_IMM,
 };
 
+static int reserved_fault_handler(struct pt_regs *regs, unsigned int esr)
+{
+	pr_err("%s generated an invalid instruction at %pS!\n",
+		in_bpf_jit(regs) ? "BPF JIT" : "Kernel text patching",
+		(void *)instruction_pointer(regs));
+
+	/* We cannot handle this */
+	return DBG_HOOK_ERROR;
+}
+
+static struct break_hook fault_break_hook = {
+	.fn = reserved_fault_handler,
+	.imm = FAULT_BRK_IMM,
+};
+
 #ifdef CONFIG_KASAN_SW_TAGS
 
 #define KASAN_ESR_RECOVER	0x20
@@ -1059,6 +1002,7 @@
 void __init trap_init(void)
 {
 	register_kernel_break_hook(&bug_break_hook);
+	register_kernel_break_hook(&fault_break_hook);
 #ifdef CONFIG_KASAN_SW_TAGS
 	register_kernel_break_hook(&kasan_break_hook);
 #endif
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index d4202a3..debb899 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -30,15 +30,11 @@
 #include <asm/vdso.h>
 
 extern char vdso_start[], vdso_end[];
-#ifdef CONFIG_COMPAT_VDSO
 extern char vdso32_start[], vdso32_end[];
-#endif /* CONFIG_COMPAT_VDSO */
 
 enum vdso_abi {
 	VDSO_ABI_AA64,
-#ifdef CONFIG_COMPAT_VDSO
 	VDSO_ABI_AA32,
-#endif /* CONFIG_COMPAT_VDSO */
 };
 
 enum vvar_pages {
@@ -284,21 +280,17 @@
 /*
  * Create and map the vectors page for AArch32 tasks.
  */
-#ifdef CONFIG_COMPAT_VDSO
 static int aarch32_vdso_mremap(const struct vm_special_mapping *sm,
 		struct vm_area_struct *new_vma)
 {
 	return __vdso_remap(VDSO_ABI_AA32, sm, new_vma);
 }
-#endif /* CONFIG_COMPAT_VDSO */
 
 enum aarch32_map {
 	AA32_MAP_VECTORS, /* kuser helpers */
-#ifdef CONFIG_COMPAT_VDSO
+	AA32_MAP_SIGPAGE,
 	AA32_MAP_VVAR,
 	AA32_MAP_VDSO,
-#endif
-	AA32_MAP_SIGPAGE
 };
 
 static struct page *aarch32_vectors_page __ro_after_init;
@@ -309,7 +301,10 @@
 		.name	= "[vectors]", /* ABI */
 		.pages	= &aarch32_vectors_page,
 	},
-#ifdef CONFIG_COMPAT_VDSO
+	[AA32_MAP_SIGPAGE] = {
+		.name	= "[sigpage]", /* ABI */
+		.pages	= &aarch32_sig_page,
+	},
 	[AA32_MAP_VVAR] = {
 		.name = "[vvar]",
 		.fault = vvar_fault,
@@ -319,11 +314,6 @@
 		.name = "[vdso]",
 		.mremap = aarch32_vdso_mremap,
 	},
-#endif /* CONFIG_COMPAT_VDSO */
-	[AA32_MAP_SIGPAGE] = {
-		.name	= "[sigpage]", /* ABI */
-		.pages	= &aarch32_sig_page,
-	},
 };
 
 static int aarch32_alloc_kuser_vdso_page(void)
@@ -362,25 +352,25 @@
 	return 0;
 }
 
-#ifdef CONFIG_COMPAT_VDSO
 static int __aarch32_alloc_vdso_pages(void)
 {
+
+	if (!IS_ENABLED(CONFIG_COMPAT_VDSO))
+		return 0;
+
 	vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
 	vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
 
 	return __vdso_init(VDSO_ABI_AA32);
 }
-#endif /* CONFIG_COMPAT_VDSO */
 
 static int __init aarch32_alloc_vdso_pages(void)
 {
 	int ret;
 
-#ifdef CONFIG_COMPAT_VDSO
 	ret = __aarch32_alloc_vdso_pages();
 	if (ret)
 		return ret;
-#endif
 
 	ret = aarch32_alloc_sigpage();
 	if (ret)
@@ -449,14 +439,12 @@
 	if (ret)
 		goto out;
 
-#ifdef CONFIG_COMPAT_VDSO
-	ret = __setup_additional_pages(VDSO_ABI_AA32,
-				       mm,
-				       bprm,
-				       uses_interp);
-	if (ret)
-		goto out;
-#endif /* CONFIG_COMPAT_VDSO */
+	if (IS_ENABLED(CONFIG_COMPAT_VDSO)) {
+		ret = __setup_additional_pages(VDSO_ABI_AA32, mm, bprm,
+					       uses_interp);
+		if (ret)
+			goto out;
+	}
 
 	ret = aarch32_sigreturn_setup(mm);
 out:
@@ -497,8 +485,7 @@
 }
 arch_initcall(vdso_init);
 
-int arch_setup_additional_pages(struct linux_binprm *bprm,
-				int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	int ret;
@@ -506,11 +493,7 @@
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
-	ret = __setup_additional_pages(VDSO_ABI_AA64,
-				       mm,
-				       bprm,
-				       uses_interp);
-
+	ret = __setup_additional_pages(VDSO_ABI_AA64, mm, bprm, uses_interp);
 	mmap_write_unlock(mm);
 
 	return ret;
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 5139a5f..d6adb46 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -208,7 +208,7 @@
       cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
 
 # Install commands for the unstripped file
-quiet_cmd_vdso_install = INSTALL $@
+quiet_cmd_vdso_install = INSTALL32 $@
       cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so
 
 vdso.so: $(obj)/vdso.so.dbg
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index ec8e894..82801d9 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -20,6 +20,13 @@
 
 jiffies = jiffies_64;
 
+
+#define HYPERVISOR_EXTABLE					\
+	. = ALIGN(SZ_8);					\
+	__start___kvm_ex_table = .;				\
+	*(__kvm_ex_table)					\
+	__stop___kvm_ex_table = .;
+
 #define HYPERVISOR_TEXT					\
 	/*						\
 	 * Align to 4 KB so that			\
@@ -35,6 +42,7 @@
 	__hyp_idmap_text_end = .;			\
 	__hyp_text_start = .;				\
 	*(.hyp.text)					\
+	HYPERVISOR_EXTABLE				\
 	__hyp_text_end = .;
 
 #define IDMAP_TEXT					\
@@ -97,7 +105,7 @@
 		*(.eh_frame)
 	}
 
-	. = KIMAGE_VADDR + TEXT_OFFSET;
+	. = KIMAGE_VADDR;
 
 	.head.text : {
 		_text = .;
@@ -266,4 +274,4 @@
 /*
  * If padding is applied before .head.text, virt<->phys conversions will fail.
  */
-ASSERT(_text == (KIMAGE_VADDR + TEXT_OFFSET), "HEAD is misaligned")
+ASSERT(_text == KIMAGE_VADDR, "HEAD is misaligned")
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 318c8f2..043756d 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -57,9 +57,6 @@
 	  Adds support for a virtual Performance Monitoring Unit (PMU) in
 	  virtual machines.
 
-config KVM_INDIRECT_VECTORS
-	def_bool HARDEN_BRANCH_PREDICTOR || RANDOMIZE_BASE
-
 endif # KVM
 
 endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 691d21e..acf9a99 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -206,6 +206,9 @@
 		 */
 		r = 1;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = kvm_arm_pvtime_supported();
+		break;
 	default:
 		r = kvm_arch_vm_ioctl_check_extension(kvm, ext);
 		break;
@@ -1256,6 +1259,40 @@
 	}
 }
 
+static int kvm_map_vectors(void)
+{
+	/*
+	 * SV2  = ARM64_SPECTRE_V2
+	 * HEL2 = ARM64_HARDEN_EL2_VECTORS
+	 *
+	 * !SV2 + !HEL2 -> use direct vectors
+	 *  SV2 + !HEL2 -> use hardened vectors in place
+	 * !SV2 +  HEL2 -> allocate one vector slot and use exec mapping
+	 *  SV2 +  HEL2 -> use hardened vectors and use exec mapping
+	 */
+	if (cpus_have_const_cap(ARM64_SPECTRE_V2)) {
+		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs);
+		__kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base);
+	}
+
+	if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) {
+		phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs);
+		unsigned long size = __BP_HARDEN_HYP_VECS_SZ;
+
+		/*
+		 * Always allocate a spare vector slot, as we don't
+		 * know yet which CPUs have a BP hardening slot that
+		 * we can reuse.
+		 */
+		__kvm_harden_el2_vector_slot = atomic_inc_return(&arm64_el2_vector_last_slot);
+		BUG_ON(__kvm_harden_el2_vector_slot >= BP_HARDEN_EL2_SLOTS);
+		return create_hyp_exec_mappings(vect_pa, size,
+						&__kvm_bp_vect_base);
+	}
+
+	return 0;
+}
+
 static void cpu_init_hyp_mode(void)
 {
 	phys_addr_t pgd_ptr;
@@ -1292,7 +1329,7 @@
 	 * at EL2.
 	 */
 	if (this_cpu_has_cap(ARM64_SSBS) &&
-	    arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
+	    arm64_get_spectre_v4_state() == SPECTRE_VULNERABLE) {
 		kvm_call_hyp_nvhe(__kvm_enable_ssbs);
 	}
 }
@@ -1549,10 +1586,6 @@
 		}
 	}
 
-	err = hyp_map_aux_data();
-	if (err)
-		kvm_err("Cannot map host auxiliary data: %d\n", err);
-
 	return 0;
 
 out_err:
@@ -1640,6 +1673,10 @@
 		return -ENODEV;
 	}
 
+	if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE))
+		kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \
+			 "Only trusted guests should be used on this system.\n");
+
 	for_each_online_cpu(cpu) {
 		smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1);
 		if (ret < 0) {
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index fe6c7d7..5d690d6 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -128,7 +128,7 @@
 	switch (ESR_ELx_EC(esr)) {
 	case ESR_ELx_EC_WATCHPT_LOW:
 		run->debug.arch.far = vcpu->arch.fault.far_el2;
-		/* fall through */
+		fallthrough;
 	case ESR_ELx_EC_SOFTSTP_LOW:
 	case ESR_ELx_EC_BREAKPT_LOW:
 	case ESR_ELx_EC_BKPT32:
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index f54f0e8..d898f0d 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -10,5 +10,4 @@
 		    -DDISABLE_BRANCH_PROFILING		\
 		    $(DISABLE_STACKLEAK_PLUGIN)
 
-obj-$(CONFIG_KVM) += vhe/ nvhe/
-obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
+obj-$(CONFIG_KVM) += vhe/ nvhe/ smccc_wa.o
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index ee32a77..76e7eaf 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -196,20 +196,23 @@
 	// This is our single instruction exception window. A pending
 	// SError is guaranteed to occur at the earliest when we unmask
 	// it, and at the latest just after the ISB.
-	.global	abort_guest_exit_start
 abort_guest_exit_start:
 
 	isb
 
-	.global	abort_guest_exit_end
 abort_guest_exit_end:
 
 	msr	daifset, #4	// Mask aborts
+	ret
 
-	// If the exception took place, restore the EL1 exception
-	// context so that we can report some information.
-	// Merge the exception code with the SError pending bit.
-	tbz	x0, #ARM_EXIT_WITH_SERROR_BIT, 1f
+	_kvm_extable	abort_guest_exit_start, 9997f
+	_kvm_extable	abort_guest_exit_end, 9997f
+9997:
+	msr	daifset, #4	// Mask aborts
+	mov	x0, #(1 << ARM_EXIT_WITH_SERROR_BIT)
+
+	// restore the EL1 exception context so that we can report some
+	// information. Merge the exception code with the SError pending bit.
 	msr	elr_el2, x2
 	msr	esr_el2, x3
 	msr	spsr_el2, x4
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 689fccb..7ea277b 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -15,6 +15,30 @@
 #include <asm/kvm_mmu.h>
 #include <asm/mmu.h>
 
+.macro save_caller_saved_regs_vect
+	/* x0 and x1 were saved in the vector entry */
+	stp	x2, x3,   [sp, #-16]!
+	stp	x4, x5,   [sp, #-16]!
+	stp	x6, x7,   [sp, #-16]!
+	stp	x8, x9,   [sp, #-16]!
+	stp	x10, x11, [sp, #-16]!
+	stp	x12, x13, [sp, #-16]!
+	stp	x14, x15, [sp, #-16]!
+	stp	x16, x17, [sp, #-16]!
+.endm
+
+.macro restore_caller_saved_regs_vect
+	ldp	x16, x17, [sp], #16
+	ldp	x14, x15, [sp], #16
+	ldp	x12, x13, [sp], #16
+	ldp	x10, x11, [sp], #16
+	ldp	x8, x9,   [sp], #16
+	ldp	x6, x7,   [sp], #16
+	ldp	x4, x5,   [sp], #16
+	ldp	x2, x3,   [sp], #16
+	ldp	x0, x1,   [sp], #16
+.endm
+
 	.text
 
 .macro do_el2_call
@@ -92,35 +116,6 @@
 			  ARM_SMCCC_ARCH_WORKAROUND_2)
 	cbnz	w1, el1_trap
 
-#ifdef CONFIG_ARM64_SSBD
-alternative_cb	arm64_enable_wa2_handling
-	b	wa2_end
-alternative_cb_end
-	get_vcpu_ptr	x2, x0
-	ldr	x0, [x2, #VCPU_WORKAROUND_FLAGS]
-
-	// Sanitize the argument and update the guest flags
-	ldr	x1, [sp, #8]			// Guest's x1
-	clz	w1, w1				// Murphy's device:
-	lsr	w1, w1, #5			// w1 = !!w1 without using
-	eor	w1, w1, #1			// the flags...
-	bfi	x0, x1, #VCPU_WORKAROUND_2_FLAG_SHIFT, #1
-	str	x0, [x2, #VCPU_WORKAROUND_FLAGS]
-
-	/* Check that we actually need to perform the call */
-	hyp_ldr_this_cpu x0, arm64_ssbd_callback_required, x2
-	cbz	x0, wa2_end
-
-	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_2
-	smc	#0
-
-	/* Don't leak data from the SMC call */
-	mov	x3, xzr
-wa2_end:
-	mov	x2, xzr
-	mov	x1, xzr
-#endif
-
 wa_epilogue:
 	mov	x0, xzr
 	add	sp, sp, #16
@@ -143,13 +138,19 @@
 	b	__guest_exit
 
 el2_sync:
-	/* Check for illegal exception return, otherwise panic */
+	/* Check for illegal exception return */
 	mrs	x0, spsr_el2
+	tbnz	x0, #20, 1f
 
-	/* if this was something else, then panic! */
-	tst	x0, #PSR_IL_BIT
-	b.eq	__hyp_panic
+	save_caller_saved_regs_vect
+	stp     x29, x30, [sp, #-16]!
+	bl	kvm_unexpected_el2_exception
+	ldp     x29, x30, [sp], #16
+	restore_caller_saved_regs_vect
 
+	eret
+
+1:
 	/* Let's attempt a recovery from the illegal exception return */
 	get_vcpu_ptr	x1, x0
 	mov	x0, #ARM_EXCEPTION_IL
@@ -157,27 +158,14 @@
 
 
 el2_error:
-	ldp	x0, x1, [sp], #16
+	save_caller_saved_regs_vect
+	stp     x29, x30, [sp, #-16]!
 
-	/*
-	 * Only two possibilities:
-	 * 1) Either we come from the exit path, having just unmasked
-	 *    PSTATE.A: change the return code to an EL2 fault, and
-	 *    carry on, as we're already in a sane state to handle it.
-	 * 2) Or we come from anywhere else, and that's a bug: we panic.
-	 *
-	 * For (1), x0 contains the original return code and x1 doesn't
-	 * contain anything meaningful at that stage. We can reuse them
-	 * as temp registers.
-	 * For (2), who cares?
-	 */
-	mrs	x0, elr_el2
-	adr	x1, abort_guest_exit_start
-	cmp	x0, x1
-	adr	x1, abort_guest_exit_end
-	ccmp	x0, x1, #4, ne
-	b.ne	__hyp_panic
-	mov	x0, #(1 << ARM_EXIT_WITH_SERROR_BIT)
+	bl	kvm_unexpected_el2_exception
+
+	ldp     x29, x30, [sp], #16
+	restore_caller_saved_regs_vect
+
 	eret
 	sb
 
@@ -271,7 +259,6 @@
 	valid_vect	el1_error		// Error 32-bit EL1
 SYM_CODE_END(__kvm_hyp_vector)
 
-#ifdef CONFIG_KVM_INDIRECT_VECTORS
 .macro hyp_ventry
 	.align 7
 1:	esb
@@ -321,4 +308,3 @@
 1:	.org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ
 	.org 1b
 SYM_CODE_END(__bp_harden_hyp_vecs)
-#endif
diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index 0297dc6..5e28ea6 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -21,70 +21,70 @@
 #define save_debug(ptr,reg,nr)						\
 	switch (nr) {							\
 	case 15:	ptr[15] = read_debug(reg, 15);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 14:	ptr[14] = read_debug(reg, 14);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 13:	ptr[13] = read_debug(reg, 13);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 12:	ptr[12] = read_debug(reg, 12);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 11:	ptr[11] = read_debug(reg, 11);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 10:	ptr[10] = read_debug(reg, 10);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 9:		ptr[9] = read_debug(reg, 9);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 8:		ptr[8] = read_debug(reg, 8);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 7:		ptr[7] = read_debug(reg, 7);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 6:		ptr[6] = read_debug(reg, 6);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 5:		ptr[5] = read_debug(reg, 5);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 4:		ptr[4] = read_debug(reg, 4);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 3:		ptr[3] = read_debug(reg, 3);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 2:		ptr[2] = read_debug(reg, 2);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 1:		ptr[1] = read_debug(reg, 1);			\
-			/* Fall through */				\
+			fallthrough;					\
 	default:	ptr[0] = read_debug(reg, 0);			\
 	}
 
 #define restore_debug(ptr,reg,nr)					\
 	switch (nr) {							\
 	case 15:	write_debug(ptr[15], reg, 15);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 14:	write_debug(ptr[14], reg, 14);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 13:	write_debug(ptr[13], reg, 13);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 12:	write_debug(ptr[12], reg, 12);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 11:	write_debug(ptr[11], reg, 11);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 10:	write_debug(ptr[10], reg, 10);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 9:		write_debug(ptr[9], reg, 9);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 8:		write_debug(ptr[8], reg, 8);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 7:		write_debug(ptr[7], reg, 7);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 6:		write_debug(ptr[6], reg, 6);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 5:		write_debug(ptr[5], reg, 5);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 4:		write_debug(ptr[4], reg, 4);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 3:		write_debug(ptr[3], reg, 3);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 2:		write_debug(ptr[2], reg, 2);			\
-			/* Fall through */				\
+			fallthrough;					\
 	case 1:		write_debug(ptr[1], reg, 1);			\
-			/* Fall through */				\
+			fallthrough;					\
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 426ef65..d0f07e8 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -17,6 +17,7 @@
 
 #include <asm/barrier.h>
 #include <asm/cpufeature.h>
+#include <asm/extable.h>
 #include <asm/kprobes.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
@@ -29,6 +30,9 @@
 
 extern const char __hyp_panic_string[];
 
+extern struct exception_table_entry __start___kvm_ex_table;
+extern struct exception_table_entry __stop___kvm_ex_table;
+
 /* Check whether the FP regs were dirtied while in the host-side run loop: */
 static inline bool update_fp_enabled(struct kvm_vcpu *vcpu)
 {
@@ -142,10 +146,10 @@
 	 * saved the guest context yet, and we may return early...
 	 */
 	par = read_sysreg(par_el1);
-	asm volatile("at s1e1r, %0" : : "r" (far));
-	isb();
-
-	tmp = read_sysreg(par_el1);
+	if (!__kvm_at("s1e1r", far))
+		tmp = read_sysreg(par_el1);
+	else
+		tmp = SYS_PAR_EL1_F; /* back to the guest */
 	write_sysreg(par, par_el1);
 
 	if (unlikely(tmp & SYS_PAR_EL1_F))
@@ -445,7 +449,7 @@
 			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
 			!kvm_vcpu_abt_issea(vcpu) &&
-			!kvm_vcpu_dabt_iss1tw(vcpu);
+			!kvm_vcpu_abt_iss1tw(vcpu);
 
 		if (valid) {
 			int ret = __vgic_v2_perform_cpuif_access(vcpu);
@@ -475,37 +479,31 @@
 	return false;
 }
 
-static inline bool __needs_ssbd_off(struct kvm_vcpu *vcpu)
+static inline void __kvm_unexpected_el2_exception(void)
 {
-	if (!cpus_have_final_cap(ARM64_SSBD))
-		return false;
+	unsigned long addr, fixup;
+	struct kvm_cpu_context *host_ctxt;
+	struct exception_table_entry *entry, *end;
+	unsigned long elr_el2 = read_sysreg(elr_el2);
 
-	return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
-}
+	entry = hyp_symbol_addr(__start___kvm_ex_table);
+	end = hyp_symbol_addr(__stop___kvm_ex_table);
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
 
-static inline void __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_ARM64_SSBD
-	/*
-	 * The host runs with the workaround always present. If the
-	 * guest wants it disabled, so be it...
-	 */
-	if (__needs_ssbd_off(vcpu) &&
-	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL);
-#endif
-}
+	while (entry < end) {
+		addr = (unsigned long)&entry->insn + entry->insn;
+		fixup = (unsigned long)&entry->fixup + entry->fixup;
 
-static inline void __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_ARM64_SSBD
-	/*
-	 * If the guest has disabled the workaround, bring it back on.
-	 */
-	if (__needs_ssbd_off(vcpu) &&
-	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL);
-#endif
+		if (addr != elr_el2) {
+			entry++;
+			continue;
+		}
+
+		write_sysreg(fixup, elr_el2);
+		return;
+	}
+
+	hyp_panic(host_ctxt);
 }
 
 #endif /* __ARM64_KVM_HYP_SWITCH_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 341be2f..8d3dd4f 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -202,8 +202,6 @@
 
 	__debug_switch_to_guest(vcpu);
 
-	__set_guest_arch_workaround_state(vcpu);
-
 	do {
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu, host_ctxt);
@@ -211,8 +209,6 @@
 		/* And we're baaack! */
 	} while (fixup_guest_exit(vcpu, &exit_code));
 
-	__set_host_arch_workaround_state(vcpu);
-
 	__sysreg_save_state_nvhe(guest_ctxt);
 	__sysreg32_save_state(vcpu);
 	__timer_disable_traps(vcpu);
@@ -270,3 +266,8 @@
 		       read_sysreg(hpfar_el2), par, vcpu);
 	unreachable();
 }
+
+asmlinkage void kvm_unexpected_el2_exception(void)
+{
+	return __kvm_unexpected_el2_exception();
+}
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 69eae60..b15d65a 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -31,7 +31,14 @@
 		isb();
 	}
 
+	/*
+	 * __load_guest_stage2() includes an ISB only when the AT
+	 * workaround is applied. Take care of the opposite condition,
+	 * ensuring that we always have an ISB, but not two ISBs back
+	 * to back.
+	 */
 	__load_guest_stage2(mmu);
+	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 
 static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 5a00735..452f4ca 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -340,10 +340,10 @@
 	case 7:
 		cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3);
 		cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2);
-		/* Fall through */
+		fallthrough;
 	case 6:
 		cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1);
-		/* Fall through */
+		fallthrough;
 	default:
 		cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0);
 	}
@@ -352,10 +352,10 @@
 	case 7:
 		cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3);
 		cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2);
-		/* Fall through */
+		fallthrough;
 	case 6:
 		cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1);
-		/* Fall through */
+		fallthrough;
 	default:
 		cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0);
 	}
@@ -373,10 +373,10 @@
 	case 7:
 		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3);
 		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2);
-		/* Fall through */
+		fallthrough;
 	case 6:
 		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1);
-		/* Fall through */
+		fallthrough;
 	default:
 		__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0);
 	}
@@ -385,10 +385,10 @@
 	case 7:
 		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3);
 		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2);
-		/* Fall through */
+		fallthrough;
 	case 6:
 		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1);
-		/* Fall through */
+		fallthrough;
 	default:
 		__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0);
 	}
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index c52d714..ecf67e6 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -131,8 +131,6 @@
 	sysreg_restore_guest_state_vhe(guest_ctxt);
 	__debug_switch_to_guest(vcpu);
 
-	__set_guest_arch_workaround_state(vcpu);
-
 	do {
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu, host_ctxt);
@@ -140,8 +138,6 @@
 		/* And we're baaack! */
 	} while (fixup_guest_exit(vcpu, &exit_code));
 
-	__set_host_arch_workaround_state(vcpu);
-
 	sysreg_save_guest_state_vhe(guest_ctxt);
 
 	__deactivate_traps(vcpu);
@@ -217,3 +213,8 @@
 	__hyp_call_panic(spsr, elr, par, host_ctxt);
 	unreachable();
 }
+
+asmlinkage void kvm_unexpected_el2_exception(void)
+{
+	return __kvm_unexpected_el2_exception();
+}
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 550dfa3..9824025 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -24,27 +24,36 @@
 		feature = smccc_get_arg1(vcpu);
 		switch (feature) {
 		case ARM_SMCCC_ARCH_WORKAROUND_1:
-			switch (kvm_arm_harden_branch_predictor()) {
-			case KVM_BP_HARDEN_UNKNOWN:
+			switch (arm64_get_spectre_v2_state()) {
+			case SPECTRE_VULNERABLE:
 				break;
-			case KVM_BP_HARDEN_WA_NEEDED:
+			case SPECTRE_MITIGATED:
 				val = SMCCC_RET_SUCCESS;
 				break;
-			case KVM_BP_HARDEN_NOT_REQUIRED:
+			case SPECTRE_UNAFFECTED:
 				val = SMCCC_RET_NOT_REQUIRED;
 				break;
 			}
 			break;
 		case ARM_SMCCC_ARCH_WORKAROUND_2:
-			switch (kvm_arm_have_ssbd()) {
-			case KVM_SSBD_FORCE_DISABLE:
-			case KVM_SSBD_UNKNOWN:
+			switch (arm64_get_spectre_v4_state()) {
+			case SPECTRE_VULNERABLE:
 				break;
-			case KVM_SSBD_KERNEL:
-				val = SMCCC_RET_SUCCESS;
-				break;
-			case KVM_SSBD_FORCE_ENABLE:
-			case KVM_SSBD_MITIGATED:
+			case SPECTRE_MITIGATED:
+				/*
+				 * SSBS everywhere: Indicate no firmware
+				 * support, as the SSBS support will be
+				 * indicated to the guest and the default is
+				 * safe.
+				 *
+				 * Otherwise, expose a permanent mitigation
+				 * to the guest, and hide SSBS so that the
+				 * guest stays protected.
+				 */
+				if (cpus_have_final_cap(ARM64_SSBS))
+					break;
+				fallthrough;
+			case SPECTRE_UNAFFECTED:
 				val = SMCCC_RET_NOT_REQUIRED;
 				break;
 			}
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 0121ef2..3d26b47 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -343,7 +343,8 @@
  * destroying the VM), otherwise another faulting VCPU may come in and mess
  * with things behind our backs.
  */
-static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size,
+				 bool may_block)
 {
 	struct kvm *kvm = mmu->kvm;
 	pgd_t *pgd;
@@ -369,11 +370,16 @@
 		 * If the range is too large, release the kvm->mmu_lock
 		 * to prevent starvation and lockup detector warnings.
 		 */
-		if (next != end)
+		if (may_block && next != end)
 			cond_resched_lock(&kvm->mmu_lock);
 	} while (pgd++, addr = next, addr != end);
 }
 
+static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+{
+	__unmap_stage2_range(mmu, start, size, true);
+}
+
 static void stage2_flush_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
 			      phys_addr_t addr, phys_addr_t end)
 {
@@ -1843,7 +1849,7 @@
 	struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
 
 	write_fault = kvm_is_write_fault(vcpu);
-	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
+	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
 
 	if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
@@ -1871,6 +1877,7 @@
 	    !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
 		force_pte = true;
 		vma_pagesize = PAGE_SIZE;
+		vma_shift = PAGE_SHIFT;
 	}
 
 	/*
@@ -1964,7 +1971,12 @@
 		(fault_status == FSC_PERM &&
 		 stage2_is_exec(mmu, fault_ipa, vma_pagesize));
 
-	if (vma_pagesize == PUD_SIZE) {
+	/*
+	 * If PUD_SIZE == PMD_SIZE, there is no real PUD level, and
+	 * all we have is a 2-level page table. Trying to map a PUD in
+	 * this case would be fatally wrong.
+	 */
+	if (PUD_SIZE != PMD_SIZE && vma_pagesize == PUD_SIZE) {
 		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
 
 		new_pud = kvm_pud_mkhuge(new_pud);
@@ -2119,7 +2131,7 @@
 			goto out;
 		}
 
-		if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+		if (kvm_vcpu_abt_iss1tw(vcpu)) {
 			kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 			ret = 1;
 			goto out_unlock;
@@ -2208,18 +2220,21 @@
 
 static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
-	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
+	unsigned flags = *(unsigned *)data;
+	bool may_block = flags & MMU_NOTIFIER_RANGE_BLOCKABLE;
+
+	__unmap_stage2_range(&kvm->arch.mmu, gpa, size, may_block);
 	return 0;
 }
 
 int kvm_unmap_hva_range(struct kvm *kvm,
-			unsigned long start, unsigned long end)
+			unsigned long start, unsigned long end, unsigned flags)
 {
 	if (!kvm->arch.mmu.pgd)
 		return 0;
 
 	trace_kvm_unmap_hva_range(start, end);
-	handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL);
+	handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, &flags);
 	return 0;
 }
 
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index f0d0312..81916e3 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -269,6 +269,7 @@
 
 	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
 		kvm_pmu_release_perf_event(&pmu->pmc[i]);
+	irq_work_sync(&vcpu->arch.pmu.overflow_work);
 }
 
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
@@ -434,6 +435,22 @@
 }
 
 /**
+ * When perf interrupt is an NMI, we cannot safely notify the vcpu corresponding
+ * to the event.
+ * This is why we need a callback to do it once outside of the NMI context.
+ */
+static void kvm_pmu_perf_overflow_notify_vcpu(struct irq_work *work)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_pmu *pmu;
+
+	pmu = container_of(work, struct kvm_pmu, overflow_work);
+	vcpu = kvm_pmc_to_vcpu(pmu->pmc);
+
+	kvm_vcpu_kick(vcpu);
+}
+
+/**
  * When the perf event overflows, set the overflow status and inform the vcpu.
  */
 static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
@@ -465,7 +482,11 @@
 
 	if (kvm_pmu_overflow_status(vcpu)) {
 		kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
-		kvm_vcpu_kick(vcpu);
+
+		if (!in_nmi())
+			kvm_vcpu_kick(vcpu);
+		else
+			irq_work_queue(&vcpu->arch.pmu.overflow_work);
 	}
 
 	cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD);
@@ -764,6 +785,9 @@
 			return ret;
 	}
 
+	init_irq_work(&vcpu->arch.pmu.overflow_work,
+		      kvm_pmu_perf_overflow_notify_vcpu);
+
 	vcpu->arch.pmu.created = true;
 	return 0;
 }
diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index 83415e9..db4056e 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -425,27 +425,30 @@
 {
 	switch (regid) {
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
-		switch (kvm_arm_harden_branch_predictor()) {
-		case KVM_BP_HARDEN_UNKNOWN:
+		switch (arm64_get_spectre_v2_state()) {
+		case SPECTRE_VULNERABLE:
 			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
-		case KVM_BP_HARDEN_WA_NEEDED:
+		case SPECTRE_MITIGATED:
 			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL;
-		case KVM_BP_HARDEN_NOT_REQUIRED:
+		case SPECTRE_UNAFFECTED:
 			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED;
 		}
 		return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
-		switch (kvm_arm_have_ssbd()) {
-		case KVM_SSBD_FORCE_DISABLE:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
-		case KVM_SSBD_KERNEL:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL;
-		case KVM_SSBD_FORCE_ENABLE:
-		case KVM_SSBD_MITIGATED:
+		switch (arm64_get_spectre_v4_state()) {
+		case SPECTRE_MITIGATED:
+			/*
+			 * As for the hypercall discovery, we pretend we
+			 * don't have any FW mitigation if SSBS is there at
+			 * all times.
+			 */
+			if (cpus_have_final_cap(ARM64_SSBS))
+				return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
+			fallthrough;
+		case SPECTRE_UNAFFECTED:
 			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED;
-		case KVM_SSBD_UNKNOWN:
-		default:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN;
+		case SPECTRE_VULNERABLE:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
 		}
 	}
 
@@ -462,14 +465,8 @@
 		val = kvm_psci_version(vcpu, vcpu->kvm);
 		break;
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
-		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
-		break;
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
 		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
-
-		if (val == KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL &&
-		    kvm_arm_get_vcpu_workaround_2_flag(vcpu))
-			val |= KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED;
 		break;
 	default:
 		return -ENOENT;
@@ -527,34 +524,35 @@
 			    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED))
 			return -EINVAL;
 
-		wa_level = val & KVM_REG_FEATURE_LEVEL_MASK;
-
-		if (get_kernel_wa_level(reg->id) < wa_level)
-			return -EINVAL;
-
 		/* The enabled bit must not be set unless the level is AVAIL. */
-		if (wa_level != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL &&
-		    wa_level != val)
+		if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) &&
+		    (val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL)
 			return -EINVAL;
 
-		/* Are we finished or do we need to check the enable bit ? */
-		if (kvm_arm_have_ssbd() != KVM_SSBD_KERNEL)
-			return 0;
-
 		/*
-		 * If this kernel supports the workaround to be switched on
-		 * or off, make sure it matches the requested setting.
+		 * Map all the possible incoming states to the only two we
+		 * really want to deal with.
 		 */
-		switch (wa_level) {
+		switch (val & KVM_REG_FEATURE_LEVEL_MASK) {
+		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL:
+		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN:
+			wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
+			break;
 		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL:
-			kvm_arm_set_vcpu_workaround_2_flag(vcpu,
-			    val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED);
-			break;
 		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED:
-			kvm_arm_set_vcpu_workaround_2_flag(vcpu, true);
+			wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED;
 			break;
+		default:
+			return -EINVAL;
 		}
 
+		/*
+		 * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the
+		 * other way around.
+		 */
+		if (get_kernel_wa_level(reg->id) < wa_level)
+			return -EINVAL;
+
 		return 0;
 	default:
 		return -ENOENT;
diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c
index f7b52ce..920ac43 100644
--- a/arch/arm64/kvm/pvtime.c
+++ b/arch/arm64/kvm/pvtime.c
@@ -13,25 +13,22 @@
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	u64 steal;
-	__le64 steal_le;
-	u64 offset;
-	int idx;
 	u64 base = vcpu->arch.steal.base;
+	u64 last_steal = vcpu->arch.steal.last_steal;
+	u64 offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
+	u64 steal = 0;
+	int idx;
 
 	if (base == GPA_INVALID)
 		return;
 
-	/* Let's do the local bookkeeping */
-	steal = vcpu->arch.steal.steal;
-	steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal;
-	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
-	vcpu->arch.steal.steal = steal;
-
-	steal_le = cpu_to_le64(steal);
 	idx = srcu_read_lock(&kvm->srcu);
-	offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
-	kvm_put_guest(kvm, base + offset, steal_le, u64);
+	if (!kvm_get_guest(kvm, base + offset, steal)) {
+		steal = le64_to_cpu(steal);
+		vcpu->arch.steal.last_steal = READ_ONCE(current->sched_info.run_delay);
+		steal += vcpu->arch.steal.last_steal - last_steal;
+		kvm_put_guest(kvm, base + offset, cpu_to_le64(steal));
+	}
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -43,7 +40,8 @@
 	switch (feature) {
 	case ARM_SMCCC_HV_PV_TIME_FEATURES:
 	case ARM_SMCCC_HV_PV_TIME_ST:
-		val = SMCCC_RET_SUCCESS;
+		if (vcpu->arch.steal.base != GPA_INVALID)
+			val = SMCCC_RET_SUCCESS;
 		break;
 	}
 
@@ -64,7 +62,6 @@
 	 * Start counting stolen time from the time the guest requests
 	 * the feature enabled.
 	 */
-	vcpu->arch.steal.steal = 0;
 	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
 
 	idx = srcu_read_lock(&kvm->srcu);
@@ -74,7 +71,7 @@
 	return base;
 }
 
-static bool kvm_arm_pvtime_supported(void)
+bool kvm_arm_pvtime_supported(void)
 {
 	return !!sched_info_on();
 }
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index ee33875..f6e8b4a 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -319,10 +319,6 @@
 		vcpu->arch.reset_state.reset = false;
 	}
 
-	/* Default workaround setup is enabled (if supported) */
-	if (kvm_arm_have_ssbd() == KVM_SSBD_KERNEL)
-		vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;
-
 	/* Reset timer */
 	ret = kvm_timer_vcpu_reset(vcpu);
 out:
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 077293b..9ca2706 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1131,6 +1131,11 @@
 		if (!vcpu_has_sve(vcpu))
 			val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
 		val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT);
+		if (!(val & (0xfUL << ID_AA64PFR0_CSV2_SHIFT)) &&
+		    arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED)
+			val |= (1UL << ID_AA64PFR0_CSV2_SHIFT);
+	} else if (id == SYS_ID_AA64PFR1_EL1) {
+		val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT);
 	} else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
 		val &= ~((0xfUL << ID_AA64ISAR1_APA_SHIFT) |
 			 (0xfUL << ID_AA64ISAR1_API_SHIFT) |
@@ -1382,6 +1387,13 @@
 	return true;
 }
 
+static bool access_mte_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	kvm_inject_undefined(vcpu);
+	return false;
+}
+
 /* sys_reg_desc initialiser for known cpufeature ID registers */
 #define ID_SANITISED(name) {			\
 	SYS_DESC(SYS_##name),			\
@@ -1547,6 +1559,10 @@
 	{ SYS_DESC(SYS_SCTLR_EL1), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
 	{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
 	{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
+
+	{ SYS_DESC(SYS_RGSR_EL1), access_mte_regs },
+	{ SYS_DESC(SYS_GCR_EL1), access_mte_regs },
+
 	{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
 	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
 	{ SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 },
@@ -1571,6 +1587,9 @@
 	{ SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi },
 	{ SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi },
 
+	{ SYS_DESC(SYS_TFSR_EL1), access_mte_regs },
+	{ SYS_DESC(SYS_TFSRE0_EL1), access_mte_regs },
+
 	{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
 	{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
 
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index 4691053..ff04443 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -23,7 +23,7 @@
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+	TP_printk("PC: 0x%016lx", __entry->vcpu_pc)
 );
 
 TRACE_EVENT(kvm_exit,
@@ -42,7 +42,7 @@
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
+	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%016lx",
 		  __print_symbolic(__entry->ret, kvm_arm_exception_type),
 		  __entry->esr_ec,
 		  __print_symbolic(__entry->esr_ec, kvm_arm_exception_class),
@@ -69,7 +69,7 @@
 		__entry->ipa			= ipa;
 	),
 
-	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
+	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#016lx",
 		  __entry->ipa, __entry->hsr,
 		  __entry->hxfar, __entry->vcpu_pc)
 );
@@ -131,7 +131,7 @@
 		__entry->cpsr			= cpsr;
 	),
 
-	TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
+	TP_printk("Emulate MMIO at: 0x%016lx (instr: %08lx, cpsr: %08lx)",
 		  __entry->vcpu_pc, __entry->instr, __entry->cpsr)
 );
 
@@ -149,7 +149,7 @@
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
+	TP_printk("mmu notifier unmap range: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -165,7 +165,7 @@
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier set pte hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_age_hva,
@@ -182,7 +182,7 @@
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
+	TP_printk("mmu notifier age hva: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -198,7 +198,7 @@
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier test age hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_set_way_flush,
diff --git a/arch/arm64/kvm/trace_handle_exit.h b/arch/arm64/kvm/trace_handle_exit.h
index 2c56d1e..8d78acc 100644
--- a/arch/arm64/kvm/trace_handle_exit.h
+++ b/arch/arm64/kvm/trace_handle_exit.h
@@ -22,7 +22,7 @@
 		__entry->is_wfe  = is_wfe;
 	),
 
-	TP_printk("guest executed wf%c at: 0x%08lx",
+	TP_printk("guest executed wf%c at: 0x%016lx",
 		  __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
 );
 
@@ -42,7 +42,7 @@
 		__entry->imm = imm;
 	),
 
-	TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)",
+	TP_printk("HVC at 0x%016lx (r0: 0x%016lx, imm: 0x%lx)",
 		  __entry->vcpu_pc, __entry->r0, __entry->imm)
 );
 
@@ -135,7 +135,7 @@
 		__entry->write_value = write_value;
 	),
 
-	TP_printk("%s %s reg %d (0x%08llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
+	TP_printk("%s %s reg %d (0x%016llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
 );
 
 TRACE_EVENT(kvm_handle_sys_reg,
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index 5c786b9..52d6f24 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -1001,8 +1001,8 @@
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 		/*
-		 * An access targetting Group0 SGIs can only generate
-		 * those, while an access targetting Group1 SGIs can
+		 * An access targeting Group0 SGIs can only generate
+		 * those, while an access targeting Group1 SGIs can
 		 * generate interrupts of either group.
 		 */
 		if (!irq->group || allow_group1) {
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 2fc2534..d31e116 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -16,3 +16,5 @@
 obj-$(CONFIG_CRC32) += crc32.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+
+obj-$(CONFIG_ARM64_MTE) += mte.o
diff --git a/arch/arm64/lib/mte.S b/arch/arm64/lib/mte.S
new file mode 100644
index 0000000..03ca6d8
--- /dev/null
+++ b/arch/arm64/lib/mte.S
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#include <linux/linkage.h>
+
+#include <asm/alternative.h>
+#include <asm/assembler.h>
+#include <asm/mte.h>
+#include <asm/page.h>
+#include <asm/sysreg.h>
+
+	.arch	armv8.5-a+memtag
+
+/*
+ * multitag_transfer_size - set \reg to the block size that is accessed by the
+ * LDGM/STGM instructions.
+ */
+	.macro	multitag_transfer_size, reg, tmp
+	mrs_s	\reg, SYS_GMID_EL1
+	ubfx	\reg, \reg, #SYS_GMID_EL1_BS_SHIFT, #SYS_GMID_EL1_BS_SIZE
+	mov	\tmp, #4
+	lsl	\reg, \tmp, \reg
+	.endm
+
+/*
+ * Clear the tags in a page
+ *   x0 - address of the page to be cleared
+ */
+SYM_FUNC_START(mte_clear_page_tags)
+	multitag_transfer_size x1, x2
+1:	stgm	xzr, [x0]
+	add	x0, x0, x1
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+SYM_FUNC_END(mte_clear_page_tags)
+
+/*
+ * Copy the tags from the source page to the destination one
+ *   x0 - address of the destination page
+ *   x1 - address of the source page
+ */
+SYM_FUNC_START(mte_copy_page_tags)
+	mov	x2, x0
+	mov	x3, x1
+	multitag_transfer_size x5, x6
+1:	ldgm	x4, [x3]
+	stgm	x4, [x2]
+	add	x2, x2, x5
+	add	x3, x3, x5
+	tst	x2, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+SYM_FUNC_END(mte_copy_page_tags)
+
+/*
+ * Read tags from a user buffer (one tag per byte) and set the corresponding
+ * tags at the given kernel address. Used by PTRACE_POKEMTETAGS.
+ *   x0 - kernel address (to)
+ *   x1 - user buffer (from)
+ *   x2 - number of tags/bytes (n)
+ * Returns:
+ *   x0 - number of tags read/set
+ */
+SYM_FUNC_START(mte_copy_tags_from_user)
+	mov	x3, x1
+	cbz	x2, 2f
+1:
+	uao_user_alternative 2f, ldrb, ldtrb, w4, x1, 0
+	lsl	x4, x4, #MTE_TAG_SHIFT
+	stg	x4, [x0], #MTE_GRANULE_SIZE
+	add	x1, x1, #1
+	subs	x2, x2, #1
+	b.ne	1b
+
+	// exception handling and function return
+2:	sub	x0, x1, x3		// update the number of tags set
+	ret
+SYM_FUNC_END(mte_copy_tags_from_user)
+
+/*
+ * Get the tags from a kernel address range and write the tag values to the
+ * given user buffer (one tag per byte). Used by PTRACE_PEEKMTETAGS.
+ *   x0 - user buffer (to)
+ *   x1 - kernel address (from)
+ *   x2 - number of tags/bytes (n)
+ * Returns:
+ *   x0 - number of tags read/set
+ */
+SYM_FUNC_START(mte_copy_tags_to_user)
+	mov	x3, x0
+	cbz	x2, 2f
+1:
+	ldg	x4, [x1]
+	ubfx	x4, x4, #MTE_TAG_SHIFT, #MTE_TAG_SIZE
+	uao_user_alternative 2f, strb, sttrb, w4, x0, 0
+	add	x0, x0, #1
+	add	x1, x1, #MTE_GRANULE_SIZE
+	subs	x2, x2, #1
+	b.ne	1b
+
+	// exception handling and function return
+2:	sub	x0, x0, x3		// update the number of tags copied
+	ret
+SYM_FUNC_END(mte_copy_tags_to_user)
+
+/*
+ * Save the tags in a page
+ *   x0 - page address
+ *   x1 - tag storage
+ */
+SYM_FUNC_START(mte_save_page_tags)
+	multitag_transfer_size x7, x5
+1:
+	mov	x2, #0
+2:
+	ldgm	x5, [x0]
+	orr	x2, x2, x5
+	add	x0, x0, x7
+	tst	x0, #0xFF		// 16 tag values fit in a register,
+	b.ne	2b			// which is 16*16=256 bytes
+
+	str	x2, [x1], #8
+
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+
+	ret
+SYM_FUNC_END(mte_save_page_tags)
+
+/*
+ * Restore the tags in a page
+ *   x0 - page address
+ *   x1 - tag storage
+ */
+SYM_FUNC_START(mte_restore_page_tags)
+	multitag_transfer_size x7, x5
+1:
+	ldr	x2, [x1], #8
+2:
+	stgm	x2, [x0]
+	add	x0, x0, x7
+	tst	x0, #0xFF
+	b.ne	2b
+
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+
+	ret
+SYM_FUNC_END(mte_restore_page_tags)
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index d91030f..5ead3c3 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,10 +4,11 @@
 				   ioremap.o mmap.o pgd.o mmu.o \
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
-obj-$(CONFIG_PTDUMP_CORE)	+= dump.o
+obj-$(CONFIG_PTDUMP_CORE)	+= ptdump.o
 obj-$(CONFIG_PTDUMP_DEBUGFS)	+= ptdump_debugfs.o
 obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_DEBUG_VIRTUAL)	+= physaddr.o
+obj-$(CONFIG_ARM64_MTE)		+= mteswap.o
 KASAN_SANITIZE_physaddr.o	+= n
 
 obj-$(CONFIG_KASAN)		+= kasan_init.o
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index a206655..001737a 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -27,6 +27,10 @@
 static DEFINE_PER_CPU(u64, reserved_asids);
 static cpumask_t tlb_flush_pending;
 
+static unsigned long max_pinned_asids;
+static unsigned long nr_pinned_asids;
+static unsigned long *pinned_asid_map;
+
 #define ASID_MASK		(~GENMASK(asid_bits - 1, 0))
 #define ASID_FIRST_VERSION	(1UL << asid_bits)
 
@@ -45,7 +49,7 @@
 	default:
 		pr_warn("CPU%d: Unknown ASID size (%d); assuming 8-bit\n",
 					smp_processor_id(),  fld);
-		/* Fallthrough */
+		fallthrough;
 	case 0:
 		asid = 8;
 		break;
@@ -72,7 +76,7 @@
 	}
 }
 
-static void set_kpti_asid_bits(void)
+static void set_kpti_asid_bits(unsigned long *map)
 {
 	unsigned int len = BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(unsigned long);
 	/*
@@ -81,13 +85,15 @@
 	 * is set, then the ASID will map only userspace. Thus
 	 * mark even as reserved for kernel.
 	 */
-	memset(asid_map, 0xaa, len);
+	memset(map, 0xaa, len);
 }
 
 static void set_reserved_asid_bits(void)
 {
-	if (arm64_kernel_unmapped_at_el0())
-		set_kpti_asid_bits();
+	if (pinned_asid_map)
+		bitmap_copy(asid_map, pinned_asid_map, NUM_USER_ASIDS);
+	else if (arm64_kernel_unmapped_at_el0())
+		set_kpti_asid_bits(asid_map);
 	else
 		bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
 }
@@ -166,6 +172,14 @@
 			return newasid;
 
 		/*
+		 * If it is pinned, we can keep using it. Note that reserved
+		 * takes priority, because even if it is also pinned, we need to
+		 * update the generation into the reserved_asids.
+		 */
+		if (refcount_read(&mm->context.pinned))
+			return newasid;
+
+		/*
 		 * We had a valid ASID in a previous life, so try to re-use
 		 * it if possible.
 		 */
@@ -256,6 +270,71 @@
 		cpu_switch_mm(mm->pgd, mm);
 }
 
+unsigned long arm64_mm_context_get(struct mm_struct *mm)
+{
+	unsigned long flags;
+	u64 asid;
+
+	if (!pinned_asid_map)
+		return 0;
+
+	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+
+	asid = atomic64_read(&mm->context.id);
+
+	if (refcount_inc_not_zero(&mm->context.pinned))
+		goto out_unlock;
+
+	if (nr_pinned_asids >= max_pinned_asids) {
+		asid = 0;
+		goto out_unlock;
+	}
+
+	if (!asid_gen_match(asid)) {
+		/*
+		 * We went through one or more rollover since that ASID was
+		 * used. Ensure that it is still valid, or generate a new one.
+		 */
+		asid = new_context(mm);
+		atomic64_set(&mm->context.id, asid);
+	}
+
+	nr_pinned_asids++;
+	__set_bit(asid2idx(asid), pinned_asid_map);
+	refcount_set(&mm->context.pinned, 1);
+
+out_unlock:
+	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+
+	asid &= ~ASID_MASK;
+
+	/* Set the equivalent of USER_ASID_BIT */
+	if (asid && arm64_kernel_unmapped_at_el0())
+		asid |= 1;
+
+	return asid;
+}
+EXPORT_SYMBOL_GPL(arm64_mm_context_get);
+
+void arm64_mm_context_put(struct mm_struct *mm)
+{
+	unsigned long flags;
+	u64 asid = atomic64_read(&mm->context.id);
+
+	if (!pinned_asid_map)
+		return;
+
+	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+
+	if (refcount_dec_and_test(&mm->context.pinned)) {
+		__clear_bit(asid2idx(asid), pinned_asid_map);
+		nr_pinned_asids--;
+	}
+
+	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+}
+EXPORT_SYMBOL_GPL(arm64_mm_context_put);
+
 /* Errata workaround post TTBRx_EL1 update. */
 asmlinkage void post_ttbr_update_workaround(void)
 {
@@ -296,8 +375,11 @@
 {
 	unsigned long num_available_asids = NUM_USER_ASIDS;
 
-	if (arm64_kernel_unmapped_at_el0())
+	if (arm64_kernel_unmapped_at_el0()) {
 		num_available_asids /= 2;
+		if (pinned_asid_map)
+			set_kpti_asid_bits(pinned_asid_map);
+	}
 	/*
 	 * Expect allocation after rollover to fail if we don't have at least
 	 * one more ASID than CPUs. ASID #0 is reserved for init_mm.
@@ -305,6 +387,13 @@
 	WARN_ON(num_available_asids - 1 <= num_possible_cpus());
 	pr_info("ASID allocator initialised with %lu entries\n",
 		num_available_asids);
+
+	/*
+	 * There must always be an ASID available after rollover. Ensure that,
+	 * even if all CPUs have a reserved ASID and the maximum number of ASIDs
+	 * are pinned, there still is at least one empty slot in the ASID map.
+	 */
+	max_pinned_asids = num_available_asids - num_possible_cpus() - 2;
 	return 0;
 }
 arch_initcall(asids_update_limit);
@@ -319,13 +408,17 @@
 		panic("Failed to allocate bitmap for %lu ASIDs\n",
 		      NUM_USER_ASIDS);
 
+	pinned_asid_map = kcalloc(BITS_TO_LONGS(NUM_USER_ASIDS),
+				  sizeof(*pinned_asid_map), GFP_KERNEL);
+	nr_pinned_asids = 0;
+
 	/*
 	 * We cannot call set_reserved_asid_bits() here because CPU
 	 * caps are not finalized yet, so it is safer to assume KPTI
 	 * and reserve kernel ASID's from beginning.
 	 */
 	if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0))
-		set_kpti_asid_bits();
+		set_kpti_asid_bits(asid_map);
 	return 0;
 }
 early_initcall(asids_init);
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index 2ee7b73..70a71f3 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -6,21 +6,32 @@
  * Copyright (C) 2012 ARM Ltd.
  */
 
+#include <linux/bitops.h>
 #include <linux/mm.h>
 
 #include <asm/page.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
+#include <asm/mte.h>
 
-void __cpu_copy_user_page(void *kto, const void *kfrom, unsigned long vaddr)
+void copy_highpage(struct page *to, struct page *from)
 {
-	struct page *page = virt_to_page(kto);
+	struct page *kto = page_address(to);
+	struct page *kfrom = page_address(from);
+
 	copy_page(kto, kfrom);
-	flush_dcache_page(page);
-}
-EXPORT_SYMBOL_GPL(__cpu_copy_user_page);
 
-void __cpu_clear_user_page(void *kaddr, unsigned long vaddr)
-{
-	clear_page(kaddr);
+	if (system_supports_mte() && test_bit(PG_mte_tagged, &from->flags)) {
+		set_bit(PG_mte_tagged, &to->flags);
+		mte_copy_page_tags(kto, kfrom);
+	}
 }
-EXPORT_SYMBOL_GPL(__cpu_clear_user_page);
+EXPORT_SYMBOL(copy_highpage);
+
+void copy_user_highpage(struct page *to, struct page *from,
+			unsigned long vaddr, struct vm_area_struct *vma)
+{
+	copy_highpage(to, from);
+	flush_dcache_page(to);
+}
+EXPORT_SYMBOL_GPL(copy_user_highpage);
diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c
index eee1732a..aa00601 100644
--- a/arch/arm64/mm/extable.c
+++ b/arch/arm64/mm/extable.c
@@ -14,9 +14,7 @@
 	if (!fixup)
 		return 0;
 
-	if (IS_ENABLED(CONFIG_BPF_JIT) &&
-	    regs->pc >= BPF_JIT_REGION_START &&
-	    regs->pc < BPF_JIT_REGION_END)
+	if (in_bpf_jit(regs))
 		return arm64_bpf_fixup_exception(fixup, regs);
 
 	regs->pc = (unsigned long)&fixup->fixup + fixup->fixup;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index f07333e..94c99c1c 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -218,7 +218,9 @@
 		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
 	} while (pteval != old_pteval);
 
-	flush_tlb_fix_spurious_fault(vma, address);
+	/* Invalidate a stale read-only entry */
+	if (dirty)
+		flush_tlb_page(vma, address);
 	return 1;
 }
 
@@ -641,6 +643,13 @@
 	return 0;
 }
 
+static int do_tag_check_fault(unsigned long addr, unsigned int esr,
+			      struct pt_regs *regs)
+{
+	do_bad_area(addr, esr, regs);
+	return 0;
+}
+
 static const struct fault_info fault_info[] = {
 	{ do_bad,		SIGKILL, SI_KERNEL,	"ttbr address size fault"	},
 	{ do_bad,		SIGKILL, SI_KERNEL,	"level 1 address size fault"	},
@@ -659,7 +668,7 @@
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
 	{ do_sea,		SIGBUS,  BUS_OBJERR,	"synchronous external abort"	},
-	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 17"			},
+	{ do_tag_check_fault,	SIGSEGV, SEGV_MTESERR,	"synchronous tag check fault"	},
 	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 18"			},
 	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 19"			},
 	{ do_sea,		SIGKILL, SI_KERNEL,	"level 0 (translation table walk)"	},
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 75df62f..936c4762 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -122,7 +122,7 @@
 	 * The following mapping attributes may be updated in live
 	 * kernel mappings without the need for break-before-make.
 	 */
-	static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
+	pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
 
 	/* creating or taking down mappings is always safe */
 	if (old == 0 || new == 0)
@@ -136,6 +136,17 @@
 	if (old & ~new & PTE_NG)
 		return false;
 
+	/*
+	 * Changing the memory type between Normal and Normal-Tagged is safe
+	 * since Tagged is considered a permission attribute from the
+	 * mismatched attribute aliases perspective.
+	 */
+	if (((old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
+	     (old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)) &&
+	    ((new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
+	     (new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)))
+		mask |= PTE_ATTRINDX_MASK;
+
 	return ((old ^ new) & ~mask) == 0;
 }
 
@@ -491,7 +502,12 @@
 		if (memblock_is_nomap(reg))
 			continue;
 
-		__map_memblock(pgdp, start, end, PAGE_KERNEL, flags);
+		/*
+		 * The linear map must allow allocation tags reading/writing
+		 * if MTE is present. Otherwise, it has the same attributes as
+		 * PAGE_KERNEL.
+		 */
+		__map_memblock(pgdp, start, end, PAGE_KERNEL_TAGGED, flags);
 	}
 
 	/*
diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c
new file mode 100644
index 0000000..c52c184
--- /dev/null
+++ b/arch/arm64/mm/mteswap.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/pagemap.h>
+#include <linux/xarray.h>
+#include <linux/slab.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <asm/mte.h>
+
+static DEFINE_XARRAY(mte_pages);
+
+void *mte_allocate_tag_storage(void)
+{
+	/* tags granule is 16 bytes, 2 tags stored per byte */
+	return kmalloc(PAGE_SIZE / 16 / 2, GFP_KERNEL);
+}
+
+void mte_free_tag_storage(char *storage)
+{
+	kfree(storage);
+}
+
+int mte_save_tags(struct page *page)
+{
+	void *tag_storage, *ret;
+
+	if (!test_bit(PG_mte_tagged, &page->flags))
+		return 0;
+
+	tag_storage = mte_allocate_tag_storage();
+	if (!tag_storage)
+		return -ENOMEM;
+
+	mte_save_page_tags(page_address(page), tag_storage);
+
+	/* page_private contains the swap entry.val set in do_swap_page */
+	ret = xa_store(&mte_pages, page_private(page), tag_storage, GFP_KERNEL);
+	if (WARN(xa_is_err(ret), "Failed to store MTE tags")) {
+		mte_free_tag_storage(tag_storage);
+		return xa_err(ret);
+	} else if (ret) {
+		/* Entry is being replaced, free the old entry */
+		mte_free_tag_storage(ret);
+	}
+
+	return 0;
+}
+
+bool mte_restore_tags(swp_entry_t entry, struct page *page)
+{
+	void *tags = xa_load(&mte_pages, entry.val);
+
+	if (!tags)
+		return false;
+
+	mte_restore_page_tags(page_address(page), tags);
+
+	return true;
+}
+
+void mte_invalidate_tags(int type, pgoff_t offset)
+{
+	swp_entry_t entry = swp_entry(type, offset);
+	void *tags = xa_erase(&mte_pages, entry.val);
+
+	mte_free_tag_storage(tags);
+}
+
+void mte_invalidate_tags_area(int type)
+{
+	swp_entry_t entry = swp_entry(type, 0);
+	swp_entry_t last_entry = swp_entry(type + 1, 0);
+	void *tags;
+
+	XA_STATE(xa_state, &mte_pages, entry.val);
+
+	xa_lock(&mte_pages);
+	xas_for_each(&xa_state, tags, last_entry.val - 1) {
+		__xa_erase(&mte_pages, xa_state.xa_index);
+		mte_free_tag_storage(tags);
+	}
+	xa_unlock(&mte_pages);
+}
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 73f8b49..676deb2 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -46,7 +46,11 @@
  */
 const struct cpumask *cpumask_of_node(int node)
 {
-	if (WARN_ON(node >= nr_node_ids))
+
+	if (node == NUMA_NO_NODE)
+		return cpu_all_mask;
+
+	if (WARN_ON(node < 0 || node >= nr_node_ids))
 		return cpu_none_mask;
 
 	if (WARN_ON(node_to_cpumask_map[node] == NULL))
@@ -448,7 +452,7 @@
  * arm64_numa_init() - Initialize NUMA
  *
  * Try each configured NUMA initialization method until one succeeds. The
- * last fallback is dummy single node config encomapssing whole memory.
+ * last fallback is dummy single node config encompassing whole memory.
  */
 void __init arm64_numa_init(void)
 {
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 23f648c..1b94f5b 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
 
+#include <asm/cacheflush.h>
 #include <asm/set_memory.h>
 #include <asm/tlbflush.h>
 
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 796e47a..23c326a 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -18,6 +18,7 @@
 #include <asm/cpufeature.h>
 #include <asm/alternative.h>
 #include <asm/smp.h>
+#include <asm/sysreg.h>
 
 #ifdef CONFIG_ARM64_64K_PAGES
 #define TCR_TG_FLAGS	TCR_TG0_64K | TCR_TG1_64K
@@ -44,14 +45,18 @@
 #define TCR_KASAN_FLAGS 0
 #endif
 
-/* Default MAIR_EL1 */
+/*
+ * Default MAIR_EL1. MT_NORMAL_TAGGED is initially mapped as Normal memory and
+ * changed during __cpu_setup to Normal Tagged if the system supports MTE.
+ */
 #define MAIR_EL1_SET							\
 	(MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRnE, MT_DEVICE_nGnRnE) |	\
 	 MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRE, MT_DEVICE_nGnRE) |	\
 	 MAIR_ATTRIDX(MAIR_ATTR_DEVICE_GRE, MT_DEVICE_GRE) |		\
 	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_NC, MT_NORMAL_NC) |		\
 	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) |			\
-	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT))
+	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT) |		\
+	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL_TAGGED))
 
 #ifdef CONFIG_CPU_PM
 /**
@@ -421,6 +426,29 @@
 	 * Memory region attributes
 	 */
 	mov_q	x5, MAIR_EL1_SET
+#ifdef CONFIG_ARM64_MTE
+	/*
+	 * Update MAIR_EL1, GCR_EL1 and TFSR*_EL1 if MTE is supported
+	 * (ID_AA64PFR1_EL1[11:8] > 1).
+	 */
+	mrs	x10, ID_AA64PFR1_EL1
+	ubfx	x10, x10, #ID_AA64PFR1_MTE_SHIFT, #4
+	cmp	x10, #ID_AA64PFR1_MTE
+	b.lt	1f
+
+	/* Normal Tagged memory type at the corresponding MAIR index */
+	mov	x10, #MAIR_ATTR_NORMAL_TAGGED
+	bfi	x5, x10, #(8 *  MT_NORMAL_TAGGED), #8
+
+	/* initialize GCR_EL1: all non-zero tags excluded by default */
+	mov	x10, #(SYS_GCR_EL1_RRND | SYS_GCR_EL1_EXCL_MASK)
+	msr_s	SYS_GCR_EL1, x10
+
+	/* clear any pending tag check faults in TFSR*_EL1 */
+	msr_s	SYS_TFSR_EL1, xzr
+	msr_s	SYS_TFSRE0_EL1, xzr
+1:
+#endif
 	msr	mair_el1, x5
 	/*
 	 * Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/ptdump.c
similarity index 97%
rename from arch/arm64/mm/dump.c
rename to arch/arm64/mm/ptdump.c
index 0b8da1c..807dc63 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/ptdump.c
@@ -41,6 +41,8 @@
 	{ 0 /* KASAN_SHADOW_START */,	"Kasan shadow start" },
 	{ KASAN_SHADOW_END,		"Kasan shadow end" },
 #endif
+	{ BPF_JIT_REGION_START,		"BPF start" },
+	{ BPF_JIT_REGION_END,		"BPF end" },
 	{ MODULES_VADDR,		"Modules start" },
 	{ MODULES_END,			"Modules end" },
 	{ VMALLOC_START,		"vmalloc() area" },
@@ -169,6 +171,10 @@
 		.mask	= PTE_ATTRINDX_MASK,
 		.val	= PTE_ATTRINDX(MT_NORMAL),
 		.set	= "MEM/NORMAL",
+	}, {
+		.mask	= PTE_ATTRINDX_MASK,
+		.val	= PTE_ATTRINDX(MT_NORMAL_TAGGED),
+		.set	= "MEM/NORMAL-TAGGED",
 	}
 };
 
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index f8912e4..ef9f1d5 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -143,14 +143,17 @@
 	}
 }
 
-static inline int bpf2a64_offset(int bpf_to, int bpf_from,
+static inline int bpf2a64_offset(int bpf_insn, int off,
 				 const struct jit_ctx *ctx)
 {
-	int to = ctx->offset[bpf_to];
-	/* -1 to account for the Branch instruction */
-	int from = ctx->offset[bpf_from] - 1;
-
-	return to - from;
+	/* BPF JMP offset is relative to the next instruction */
+	bpf_insn++;
+	/*
+	 * Whereas arm64 branch instructions encode the offset
+	 * from the branch itself, so we must subtract 1 from the
+	 * instruction offset.
+	 */
+	return ctx->offset[bpf_insn + off] - (ctx->offset[bpf_insn] - 1);
 }